@prefix rdf: . @prefix sl: . @prefix skos: . @prefix rdfs: . @prefix tag: . @prefix foaf: . @prefix dc: . tag:knowledge_graph_embeddings a sl:Tag ; skos:prefLabel "Knowledge Graph Embeddings" . tag:solr a sl:Tag ; skos:prefLabel "Solr" . tag:gpt_4 a sl:Tag ; skos:prefLabel "GPT-4" . tag:benchmark a sl:Tag ; skos:prefLabel "Benchmark" . dc:title "microsoft/chat-copilot" ; sl:creationDate "2023-11-16" ; sl:tag tag:semantic_kernel . dc:title "huggingface/pytorch-transformers: A library of state-of-the-art pretrained models for NLP" ; sl:comment "(formerly known as pytorch-pretrained-bert)" ; sl:creationDate "2019-07-27" ; sl:tag tag:attention_is_all_you_need , tag:pytorch , tag:pretrained_models , tag:github_project . dc:title "GitHub - solid/solid: Solid - Re-decentralizing the web (project directory)" ; sl:creationDate "2018-03-27" ; sl:tag tag:solid , tag:github_project . dc:title "castagna/jena-examples · GitHub" ; sl:creationDate "2012-12-09" ; sl:tag tag:jena_dev , tag:github_project . tag:sparse_dense a sl:Tag ; skos:prefLabel "Sparse+Dense" . tag:ruben_verborgh a sl:Tag ; skos:prefLabel "Ruben Verborgh" . dc:title "BiLSTM-CNN-CRF Implementation for Sequence Tagging" ; sl:comment "([linked from here](http://nlp.town/blog/ner-and-the-road-to-deep-learning/))" ; sl:creationDate "2018-05-21" ; sl:tag tag:sequence_labeling , tag:named_entity_recognition , tag:github_project , tag:bi_lstm . tag:similarity_queries a sl:Tag ; skos:prefLabel "Similarity queries / Vector search" . tag:node_js a sl:Tag ; skos:prefLabel "node.js" . tag:aterm a sl:Tag ; skos:prefLabel "ATerm" . tag:synthetic_qa_data a sl:Tag ; skos:prefLabel "Synthetic QA data" . tag:nlp_amazon a sl:Tag ; skos:prefLabel "NLP@Amazon" . tag:mlm a sl:Tag ; skos:prefLabel "MLM" . tag:markdown_ittt a sl:Tag ; skos:prefLabel "markdown-it" . dc:title "Layout-Parser/layout-parser: A Unified Toolkit for Deep Learning Based Document Image Analysis" ; sl:comment "[Customizing LayoutParser Models with Label Studio Annotation (With Scientific Document Parsing as an example)](https://github.com/Layout-Parser/layout-parser/blob/main/examples/Customizing%20Layout%20Models%20with%20Label%20Studio%20Annotation/Customizing%20Layout%20Models%20with%20Label%20Studio%20Annotation.ipynb) ([#Label Studio](tag:label_studio))" ; sl:creationDate "2023-01-10" ; sl:tag tag:layout_parser , tag:github_project . tag:nlp_ibm a sl:Tag ; skos:prefLabel "NLP@IBM" . tag:llama_2 a sl:Tag ; skos:prefLabel "Llama 2" . dc:title "Thomas Wolf sur Twitter : \"you can divide the size of any model in 🤗 transformers: model.int8()\"" ; sl:creationDate "2022-09-26" ; sl:tag tag:tweet , tag:nn_tips , tag:huggingface_transformers . dc:title "ringgaard/sling: SLING - A natural language frame semantics parser" ; sl:comment "[Try It](doc:2021/03/wikidata_browser)" ; sl:creationDate "2021-03-08" ; sl:tag tag:wikidata_browser , tag:github_project . tag:nlp_text_classification a sl:Tag ; skos:prefLabel "Text Classification" . tag:approximate_nearest_neighbor a sl:Tag ; skos:prefLabel "Approximate nearest-neighbor" . tag:siamese_network a sl:Tag ; skos:prefLabel "Siamese networks" . tag:sample_code a sl:Tag ; skos:prefLabel "Sample code" . tag:retriever_reader a sl:Tag ; skos:prefLabel "Retriever-Reader" . tag:speech_recognition a sl:Tag ; skos:prefLabel "Speech-to-Text" . tag:acl_2021 a sl:Tag ; skos:prefLabel "ACL 2021" . tag:github a sl:Tag ; skos:prefLabel "GitHub" . tag:wikidata_browser a sl:Tag ; skos:prefLabel "Wikidata browser" . dc:title "Which flavor of BERT should you use for your QA task? | by Olesya Bondarenko | Towards Data Science" ; sl:comment "A guide to choosing and benchmarking BERT models for question answering" ; sl:creationDate "2020-10-04" ; sl:tag tag:tutorial , tag:question_answering , tag:huggingface_transformers , tag:bert . tag:sense2vec a sl:Tag ; skos:prefLabel "Sense2vec" . dc:title "Zshot: Zero and Few shot named entity & relationships recognition" ; sl:creationDate "2022-10-01" ; sl:tag tag:zero_shot , tag:relation_extraction , tag:nlp_ibm , tag:named_entity_recognition , tag:github_project , tag:few_shot_learning . dc:title "rakuten-nlp/category2vec (2015)" ; sl:creationDate "2019-08-05" ; sl:tag tag:github_project , tag:category_embedding . tag:ml_deploy a sl:Tag ; skos:prefLabel "ML: deploy" . tag:rake a sl:Tag ; skos:prefLabel "RAKE" . dc:title "huggingface/tokenizers: Fast State-of-the-Art Tokenizers optimized for Research and Production" ; sl:creationDate "2020-01-11" ; sl:tag tag:hugging_face , tag:github_project . dc:title "GitHub - tensorflow/models: Models and examples built with TensorFlow" ; sl:creationDate "2018-02-28" ; sl:tag tag:tensorflow , tag:sample_code , tag:github_project . tag:semantic_kernel a sl:Tag ; skos:broader tag:github_project ; skos:prefLabel "Semantic Kernel" . tag:sylvain_gugger a sl:Tag ; skos:prefLabel "Sylvain Gugger" . tag:beir a sl:Tag ; skos:prefLabel "BEIR" . tag:medical_ir_ml_ia a sl:Tag ; skos:prefLabel "Medical IR, ML, IA" . dc:title "facebookresearch/DrQA: Reading Wikipedia to Answer Open-Domain Questions" ; sl:comment "> approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs" ; sl:creationDate "2021-12-08" ; sl:tag tag:wikipedia , tag:open_domain_question_answering , tag:nlp_facebook , tag:github_project , tag:discussed_with_ns , tag:acl_2017 . tag:lime a sl:Tag ; skos:prefLabel "LIME" . dc:title "pfliu-nlp/Named-Entity-Recognition-NER-Papers: An elaborate and exhaustive paper list for Named Entity Recognition (NER)" ; sl:creationDate "2020-01-12" ; sl:tag tag:research_papers , tag:named_entity_recognition , tag:github_project . tag:python_sample_code a sl:Tag ; skos:prefLabel "Python sample code" . tag:sequence_to_sequence_learning a sl:Tag ; skos:prefLabel "Sequence-to-sequence learning" . tag:java a sl:Tag ; skos:prefLabel "Java" . dc:title "Transformer models - Hugging Face Course" ; sl:creationDate "2021-06-15" ; sl:tag tag:tutorial , tag:huggingface_transformers . dc:title "Old semanlink schema in a github project!" ; sl:creationDate "2013-09-13" ; sl:tag tag:semanlink , tag:github_project . tag:entity_linking a sl:Tag ; skos:prefLabel "Entity linking" . tag:nils_reimers a sl:Tag ; skos:prefLabel "Nils Reimers" . tag:google_knowledge_graph a sl:Tag ; skos:prefLabel "Google Knowledge Graph" . dc:title "Hugging Face Transformer Inference Under 1 Millisecond Latency | by Michaël Benesty | Towards Data Science" ; sl:creationDate "2022-06-13" ; sl:tag tag:onnx , tag:ml_deploy , tag:huggingface_transformers . dc:title "raphaelsty/mkb: Knowledge Base Embedding By Cooperative Knowledge Distillation" ; sl:creationDate "2020-07-24" ; sl:tag tag:raphaelsty , tag:kd_mkb , tag:github_project . dc:title "tloen/alpaca-lora: Instruct-tune LLaMA on consumer hardware" ; sl:comment "Uses [LoRA: Low-Rank Adaptation of Large Language Models](doc:2023/03/2106_09685_lora_low_rank_ada)\r\n\r\nsee [Alpaca Finetuning of Llama on a 24G Consumer GPU](doc:2023/03/alpaca_finetuning_of_llama_on_a)" ; sl:creationDate "2023-03-22" ; sl:tag tag:llama , tag:gpt_frugal_alternatives , tag:github_project , tag:alpaca . dc:title "Hydra Community Group - GitHub" ; sl:comment "Issues\r\n\r\n" ; sl:creationDate "2015-02-18" ; sl:tag tag:hydra , tag:github_project . tag:open_domain_question_answering a sl:Tag ; skos:prefLabel "Open Domain Question Answering" . dc:title "k-Nearest Neighbor lookups on embeddings: kNN vs SVM" ; sl:comment "> A very common workflow is to index some data based on its embeddings and then given a new query embedding retrieve the most similar examples with k-Nearest Neighbor search.\r\n> in my experience it **~always works better to use an SVM instead of kNN**, if you can afford the slight computational hit.\"\r\n\r\n> can accommodate a number of positives not just one\r\n\r\n> works because SVM ranking considers the unique aspects of your query w.r.t. data.\r\n\r\n> [Fun weekend hack: awesome-movies.life...](doc:2023/04/andrej_karpathy_sur_twitter__1)\r\n\r\n[Tweet](https://twitter.com/karpathy/status/1647025230546886658) ; in [LangChain](https://twitter.com/hwchase17/status/1647328542529843200?s=20)" ; sl:creationDate "2023-04-15" ; sl:tag tag:support_vector_machine , tag:similarity_queries , tag:k_nearest_neighbors_algorithm , tag:github_project , tag:andrej_karpathy . tag:react_js a sl:Tag ; skos:prefLabel "React.js" . tag:chatgpt a sl:Tag ; skos:prefLabel "ChatGPT" . dc:title "Extractive Question Answering - Hugging Face transformers doc" ; sl:creationDate "2021-11-18" ; sl:tag tag:huggingface_transformers , tag:extractive_question_answering . dc:title "MD-LD" ; sl:comment "MD-LD extends Markdown's reference link syntax to allow easy authoring of structured data." ; sl:creationDate "2015-10-04" ; sl:tag tag:markdown , tag:json_ld , tag:github_project . tag:knn_transformers a sl:Tag ; skos:prefLabel "kNN-Transformers" . tag:zero_shot a sl:Tag ; skos:prefLabel "Zero shot" . dc:title "semi-technologies/weaviate: Weaviate is a cloud-native, modular, real-time vector search engine" ; sl:comment "> vector search engine and vector database. Weaviate uses machine learning to vectorize and store data, and to find answers to natural language queries. " ; sl:creationDate "2021-12-05" ; sl:tag tag:weaviate , tag:vector_database , tag:similarity_queries , tag:nlp_tools , tag:neural_models_for_information_retrieval , tag:github_project . dc:title "Accenture/AmpliGraph: Python library for Representation Learning on Knowledge Graphs" ; sl:comment "Open source Python library that predicts links between concepts in a knowledge graph." ; sl:creationDate "2019-03-25" ; sl:tag tag:knowledge_graph_embeddings , tag:github_project . tag:text_similarity a sl:Tag ; skos:prefLabel "Text Similarity" . tag:nlp_topic_extraction a sl:Tag ; skos:prefLabel "Keyword/keyphrase extraction" . tag:pretrained_models a sl:Tag ; skos:prefLabel "Pretrained models" . tag:extractive_question_answering a sl:Tag ; skos:prefLabel "Extractive Question Answering" . tag:tweet a sl:Tag ; skos:prefLabel "Tweet" . dc:title "word2vec-api" ; sl:comment "Simple web service providing a word embedding API. The methods are based on Gensim Word2Vec implementation.
\r\nList of word2vec datasets\r\n" ; sl:creationDate "2017-06-09" ; sl:tag tag:word2vec , tag:github_project , tag:gensim , tag:francois_scharffe . dc:title "Sylvain Gugger sur Twitter : \"Training a transformer model for text classification...\"" ; sl:creationDate "2020-10-19" ; sl:tag tag:nlp_text_classification , tag:sylvain_gugger , tag:huggingface_transformers . tag:ragatouille a sl:Tag ; skos:prefLabel "RAGatouille" . dc:title "bclavie/RAGatouille" ; sl:comment "> RAGatouille's purpose is make it easy to use state-of-the-art methods in your RAG pipeline, without having to worry about the details or the years of literature! At the moment, RAGatouille focuses on making ColBERT simple to use.\r\n\r\n[Using ColBERT in-memory: Index-Free Encodings & Search](https://github.com/bclavie/RAGatouille/blob/0.0.5b1/examples/06-index_free_use.ipynb)\r\n```\r\nfrom ragatouille import RAGPretrainedModel\r\nRAG = RAGPretrainedModel.from_pretrained \"colbert-ir/colbertv2. 0\" )\r\n# Your documents, a plain old list of chunked strings.\r\ndocuments = [...]\r\n# In-memory indexing supports metadata too!\r\nmeta = ['attribute': ' really cool value'}...]\r\n# All the magic happens here\r\nRAG.encode documents, document_metadatas=meta)\r\n# Query your in-memory index\r\nRAG. search_encoded_docs(query = \"A great question\", k=3)\r\n# All further encode() calls add to the existing documents...\r\nRAG.encode(extra_documents, document_metadatas=extra_meta)\r\n# ... until you clear them\r\nRAG.clear_encoded\r\n```" ; sl:creationDate "2024-01-26" ; sl:tag tag:ragatouille , tag:retrieval_augmented_generation , tag:github_project , tag:colbert , tag:benjamin_clavie . dc:title "huggingface/setfit: Efficient few-shot learning with Sentence Transformers" ; sl:creationDate "2022-10-12" ; sl:tag tag:setfit_sbert_fine_tuning , tag:github_project . dc:title "facebookresearch/faiss: A library for efficient similarity search and clustering of dense vectors." ; sl:comment "Algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. Faiss is written in C++ with complete wrappers for Python/numpy.\r\n\r\n[paper](https://arxiv.org/abs/1702.08734)" ; sl:creationDate "2020-06-09" ; sl:tag tag:nearest_neighbor_search , tag:locality_sensitive_hashing , tag:kd_mkb_biblio , tag:github_project , tag:faiss , tag:facebook_fair . dc:title "D3: Data-Driven Documents" ; sl:comment "JavaScript library for visualizing data using web standards (SVG, Canvas and HTML). D3 combines visualization and interaction techniques with a data-driven approach to DOM manipulation" ; sl:creationDate "2017-06-28" ; sl:tag tag:github_project , tag:d3js . dc:title "neulab/knn-transformers: PyTorch code for the RetoMaton paper: \"Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval\" (ICML 2022), including an implementation of kNN-LM and kNN-MT" ; sl:comment "> a Hugging Face's transformers implementation of k-nearest-neighbor-based language models and machine translation models, designed to be easy and useful in research, and for experimenting with new ideas in kNN-based models.\r\n\r\ncf. \r\n\r\n- [[1911.00172] Generalization through Memorization: Nearest Neighbor Language Models](doc:2019/12/_1911_00172_generalization_thr)\r\n- [[2201.12431] Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval](doc:2022/07/2201_12431_neuro_symbolic_lan)" ; sl:creationDate "2022-07-21" ; sl:tag tag:knn_transformers , tag:github_project . tag:json_ld a sl:Tag ; skos:prefLabel "JSON-LD" . tag:github_project a sl:Tag ; rdfs:isDefinedBy ; skos:broader tag:github ; skos:prefLabel "GitHub project" ; foaf:page tag:github_project.html . dc:title "Joint Intent Classification and Slot Filling with Transformers (Jupyter Notebook Viewer)" ; sl:comment "tutorial to build a simple Natural Language Understanding system using the \r\n@snips\r\n voice assistant dataset (English only)." ; sl:creationDate "2020-01-09" ; sl:tag tag:tutorial , tag:sample_code , tag:olivier_grisel , tag:intent_classification_and_slot_filling , tag:huggingface_transformers . tag:question_answering a sl:Tag ; skos:prefLabel "Question Answering" . tag:nlp_french a sl:Tag ; skos:prefLabel "NLP: French" . tag:facebook a sl:Tag ; skos:prefLabel "Facebook" . dc:title "GitHub - spotify/annoy: Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk" ; sl:creationDate "2018-03-12" ; sl:tag tag:github_project , tag:approximate_nearest_neighbor . dc:title "karpathy/nanoGPT: The simplest, fastest repository for training/finetuning medium-sized GPTs." ; sl:creationDate "2023-02-02" ; sl:tag tag:openai_gpt , tag:github_project , tag:fine_tuning , tag:andrej_karpathy . dc:title "GitHub - explosion/sense2vec: Contextually-keyed word vectors" ; sl:creationDate "2020-12-31" ; sl:tag tag:sense2vec , tag:github_project . dc:title "Unsupervised_Extractive_Summarization - a Hugging Face Space by Hellisotherpeople" ; sl:comment "Unsupervised Extractive Text Summarization and Semantic Search\r\n\r\n[Github](https://github.com/Hellisotherpeople/CX_DB8)" ; sl:creationDate "2021-12-03" ; sl:tag tag:sbert , tag:github_project , tag:extractive_summarization . tag:retrieval_augmented_lm a sl:Tag ; skos:prefLabel "Retrieval augmented LM" . tag:extractive_summarization a sl:Tag ; skos:prefLabel "Extractive Text Summarization" . dc:title "mayooear/gpt4-pdf-chatbot-langchain: GPT4 & LangChain Chatbot for large PDF docs" ; sl:comment "> \"How to chat with a 56-page PDF\"" ; sl:creationDate "2023-04-20" ; sl:tag tag:langchain , tag:gpt_4 , tag:github_project , tag:pdf_chat , tag:chatbot . dc:title "Elastic Transformers. Making BERT stretchy — Scalable… | by Mihail Dungarov | Sep, 2020 | Medium" ; sl:creationDate "2020-09-08" ; sl:tag tag:huggingface_transformers , tag:elasticsearch . tag:domain_adaptation_new_vocab a sl:Tag ; skos:prefLabel "Domain adaptation: vocabulary" . dc:title "How I almost won an NLP competition without knowing any Machine Learning - DEV Community" ; sl:creationDate "2021-08-11" ; sl:tag tag:huggingface_transformers , tag:howto . tag:llm_code a sl:Tag ; skos:prefLabel "LLM + Code" . dc:title "awslabs/dgl-ke: package for learning large-scale knowledge graph embeddings." ; sl:creationDate "2020-07-07" ; sl:tag tag:kg_embeddings_library , tag:github_project , tag:ai_amazon . tag:nlp_based_ir a sl:Tag ; skos:prefLabel "NLP based IR" . tag:nlp_tools a sl:Tag ; skos:prefLabel "NLP tools" . tag:colbert a sl:Tag ; skos:prefLabel "ColBERT" . tag:documentation a sl:Tag ; skos:prefLabel "Documentation" . dc:title "asahi417/tner: Language model finetuning on NER" ; sl:creationDate "2021-03-04" ; sl:tag tag:named_entity_recognition , tag:huggingface_transformers , tag:github_project . tag:recommended_reading a sl:Tag ; skos:prefLabel "Recommended reading" . dc:title "Zero-shot classifier distillation at master · huggingface/transformers" ; sl:comment "This script provides a way to improve the speed and memory performance of a zero-shot classifier by training a more efficient student model from the zero-shot teacher's predictions over an unlabeled dataset." ; sl:creationDate "2021-02-23" ; sl:tag tag:zero_shot_text_classifier , tag:knowledge_distillation , tag:huggingface_transformers , tag:github_project . dc:title "UKPLab/sentence-transformers: Sentence Embeddings with BERT & XLNet" ; sl:comment "[paper](doc:2019/08/_1908_10084_sentence_bert_sen)" ; sl:creationDate "2020-07-14" ; sl:tag tag:xlnet , tag:sbert , tag:huggingface_transformers , tag:github_project . tag:huggingface_transformers a sl:Tag ; skos:broader tag:github_project ; skos:prefLabel "huggingface / transformers" . tag:cherche_raphael a sl:Tag ; skos:broader tag:github_project ; skos:prefLabel "Cherche (Raphaël)" . dc:title "RDFLib/rdflib: a Python library for working with RDF" ; sl:comment "[doc](https://rdflib.readthedocs.io/en/stable/)" ; sl:creationDate "2020-04-09" ; sl:tag tag:rdflib , tag:github_project . tag:raphael_troncy a sl:Tag ; skos:prefLabel "Raphaël Troncy" . dc:title "ATOM documentation" ; sl:creationDate "2014-10-05" ; sl:tag tag:documentation , tag:atom_github . dc:title "StarCoder: A State-of-the-Art LLM for Code" ; sl:creationDate "2023-10-01" ; sl:tag tag:llm_code , tag:github_project . tag:nlp_princeton a sl:Tag ; skos:prefLabel "NLP@Princeton" . tag:atom_github a sl:Tag ; skos:broader tag:github_project ; skos:prefLabel "ATOM (Text editor)" . tag:evilstreak_markdown_js a sl:Tag ; skos:broader tag:github_project ; skos:prefLabel "evilstreak/markdown-js" . dc:title "merve sur Twitter : \"@huggingface transformers includes a new pipeline called Document Question Answering. This is a pipeline you can use to extract information from PDFs!..." ; sl:comment "[other tweet](https://twitter.com/osanseviero/status/1572332963378958338?s=20&t=Ipu3j81b5g7_sxHvh6AXuw)" ; sl:creationDate "2022-09-20" ; sl:tag tag:tweet , tag:question_answering , tag:huggingface_transformers , tag:pdf_extract . tag:chatgpt_programming a sl:Tag ; skos:prefLabel "ChatGPT: programming" . dc:title "online-ml/river (Online machine learning in Python)" ; sl:comment "Python library for online machine learning (ML on streaming data). Merge between creme and scikit-multiflow. [Paper](doc:2021/01/2012_04740_river_machine_lea)" ; sl:creationDate "2020-01-01" ; sl:tag tag:raphaelsty , tag:max_halford , tag:github_project , tag:continual_learning . dc:title "ZhangShiyue/QGforQA" ; sl:comment "Source code for the systems described in: [Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering](doc:2021/12/1909_06356_addressing_semanti)" ; sl:creationDate "2021-12-08" ; sl:tag tag:synthetic_qa_data , tag:semi_supervised_qa , tag:github_project , tag:emnlp_2019 , tag:discussed_with_ns . tag:xlnet a sl:Tag ; skos:prefLabel "XLNet" . tag:ai_amazon a sl:Tag ; skos:prefLabel "AI@Amazon" . dc:title "Ankur Goyal sur Twitter : \"DocQuery, a new #opensource query engine for analyzing documents using large language models (LLMs)...\"" ; sl:comment "> DocQuery: Document Query Engine Powered by NLP" ; sl:creationDate "2022-09-01" ; sl:tag tag:tweet , tag:huggingface_transformers , tag:document_processing , tag:2d_nlp . tag:discute_avec_raphael a sl:Tag ; skos:prefLabel "Discuté avec Raphaël" . tag:biterm_topic_model a sl:Tag ; skos:prefLabel "Biterm Topic Model" . tag:rdf2rdfa a sl:Tag ; skos:prefLabel "RDF2RDFa" . tag:splade a sl:Tag ; skos:prefLabel "SPLADE" . tag:neural_machine_translation a sl:Tag ; skos:prefLabel "Neural machine translation" . tag:attention_is_all_you_need a sl:Tag ; skos:prefLabel "Transformers" . tag:semanlink a sl:Tag ; skos:prefLabel "Semanlink" . tag:pytorch a sl:Tag ; skos:prefLabel "PyTorch" . dc:title "thunlp/OpenKE: An Open-Source Package for Knowledge Embedding (KE)" ; sl:comment "[paper at EMNLP 2018](https://www.aclweb.org/anthology/papers/D/D18/D18-2024/)" ; sl:creationDate "2019-04-23" ; sl:tag tag:knowledge_graph_embeddings , tag:github_project , tag:emnlp_2018 . dc:title "Hugging Face sur Twitter : \"No labeled data? No problem. The 🤗 Transformers master branch now includes a built-in pipeline for zero-shot text classification..." ; sl:creationDate "2020-08-12" ; sl:tag tag:zero_shot , tag:nlp_text_classification , tag:nlp_sample_code , tag:huggingface_transformers . dc:title "huggingface/pytorch-pretrained-BERT: The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL." ; sl:creationDate "2019-03-15" ; sl:tag tag:pytorch , tag:github_project , tag:bert . tag:topic_modeling a sl:Tag ; skos:prefLabel "Topic Modeling" . dc:title "facebookresearch/UnsupervisedQA: Unsupervised Question answering via Cloze Translation" ; sl:comment "> This repository provides code to run pre-trained models to generate synthetic question answering question data. We also make a very large synthetic training dataset for extractive question answering available.\r\n\r\n[Paper](doc:2021/12/1906_04980_unsupervised_quest)" ; sl:creationDate "2021-12-07" ; sl:tag tag:nlp_datasets , tag:extractive_question_answering , tag:synthetic_qa_data , tag:nlp_facebook , tag:discussed_with_ns , tag:unsupervised_qa , tag:github_project . tag:python a sl:Tag ; skos:prefLabel "Python" . tag:chrome_extension a sl:Tag ; skos:prefLabel "Chrome extension" . tag:servlet a sl:Tag ; skos:prefLabel "Servlet" . dc:title "Dexx Collections: Persistent (immutable) collections for Java" ; sl:comment "a port of Scala's immutable, persistent collection classes to pure Java." ; sl:creationDate "2017-01-06" ; sl:tag tag:persistent_data_structure , tag:github_project . tag:these_renault_embeddings a sl:Tag ; skos:prefLabel "Thèse IRIT-Renault NLP-KB" . tag:faiss a sl:Tag ; skos:prefLabel "faiss" . tag:omar_khattab a sl:Tag ; skos:prefLabel "Omar Khattab" . dc:title "A knowledge graph embedding library for reproducible research" ; sl:comment "PyTorch-based library for training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). Cf. ICLR Paper: [You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings](/doc/2020/05/you_can_teach_an_old_dog_new_tr)" ; sl:creationDate "2020-05-04" ; sl:tag tag:reproducible_research , tag:knowledge_graph_embeddings , tag:github_project . tag:allennlp a sl:Tag ; skos:prefLabel "AllenNLP" . dc:title "How to use BERT for finding similar sentences or similar news? · Issue #876 · huggingface/transformers" ; sl:comment "links to [UKPLab/sentence-transformers](doc:2020/07/ukplab_sentence_transformers_s)\r\n\r\n[Another answer](https://github.com/huggingface/transformers/issues/2986)\r\n\r\n" ; sl:creationDate "2020-07-12" ; sl:tag tag:huggingface_transformers , tag:bert_and_sentence_embeddings . dc:title "Maria Khalusova @maria@recsys.social sur Twitter : \"Did you know that you can tweak the text output generated by a LLM without changing any of the trainable parameters?...\"" ; sl:comment "just tweak the text generation strategy" ; sl:creationDate "2023-02-23" ; sl:tag tag:tweet , tag:llm , tag:huggingface_transformers , tag:gpt_2 . dc:title "NLP | How to add a domain-specific vocabulary (new tokens) to a subword tokenizer already trained like BERT WordPiece | by Pierre Guillou | Medium" ; sl:creationDate "2022-03-18" ; sl:tag tag:lm_adaptation_to_domain , tag:huggingface_transformers , tag:domain_specific_bert , tag:domain_adaptation_new_vocab . tag:sequence_labeling a sl:Tag ; skos:prefLabel "Sequence labeling" . tag:youtube_video a sl:Tag ; skos:prefLabel "YouTube video" . dc:title "dicksontsai/stanford-nlp-local-extension: Chrome extension for sending content to localhost server running Stanford NLP tools." ; sl:creationDate "2020-07-03" ; sl:tag tag:stanford_pos_tagger , tag:servlet , tag:sample_code , tag:github_project , tag:chrome_extension . tag:google_colab a sl:Tag ; skos:prefLabel "Google Colab" . tag:chatgpt_over_your_data a sl:Tag ; skos:prefLabel "ChatGPT Over Your Data" . tag:llama a sl:Tag ; skos:prefLabel "LLaMA" . dc:title "dmmiller612/bert-extractive-summarizer: Easy to use extractive text summarization with BERT" ; sl:creationDate "2022-10-28" ; sl:tag tag:github_project , tag:extractive_summarization . tag:gensim a sl:Tag ; skos:prefLabel "gensim" . tag:unsupervised_qa a sl:Tag ; skos:prefLabel "Unsupervised QA" . dc:title "huggingface/transformers: 🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch." ; sl:comment "(BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet, CTRL...) with over 32+ pretrained models in 100+ languages and deep interoperability between TensorFlow 2.0 and PyTorch.\r\n\r\n[doc](https://huggingface.co/transformers/)" ; sl:creationDate "2019-11-16" ; sl:tag tag:attention_is_all_you_need , tag:huggingface_transformers , tag:hugging_face , tag:github_project . tag:jackson a sl:Tag ; skos:prefLabel "Jackson" . dc:title "pemistahl/lingua: natural language detection library for Java suitable for long and short text alike" ; sl:creationDate "2020-12-12" ; sl:tag tag:language_identification , tag:java , tag:github_project . tag:pdf_chat a sl:Tag ; skos:prefLabel "Chat over your PDFs" . tag:rdf_owl_documentation_tool a sl:Tag ; skos:prefLabel "RDF-OWL documentation tool" . dc:title "Sahajtomar/french_semantic · Hugging Face" ; sl:creationDate "2021-10-14" ; sl:tag tag:sbert , tag:nlp_french , tag:huggingface_transformers , tag:discute_avec_raphael , tag:camembert_nlp . dc:title "TheAppleTucker/backend-GPT \"GPT is all you need for the backend\"" ; sl:comment "> We've built a entire Backend+Database powered by an LLM. It infers business logic based on the name of the API call and can persist a kilobyte of state!\r\n\r\n[Tweet](https://twitter.com/DYtweetshere/status/1617471632909676544)" ; sl:creationDate "2023-01-25" ; sl:tag tag:github_project , tag:chatgpt_programming . tag:open_source a sl:Tag ; skos:prefLabel "Open Source" . dc:title "adapter-hub/adapter-transformers: Huggingface Transformers + Adapters" ; sl:creationDate "2022-07-22" ; sl:tag tag:huggingface_transformers , tag:github_project , tag:adapter_modules_finetuning . dc:title "SolRDF - GitHub" ; sl:comment "SolRDF (i.e. Solr + RDF) is a set of Solr extensions for managing (index and search) RDF data." ; sl:creationDate "2014-12-23" ; sl:tag tag:solr , tag:github_project . tag:support_vector_machine a sl:Tag ; skos:prefLabel "SVM" . tag:python_library a sl:Tag ; skos:prefLabel "Python library" . tag:weaviate a sl:Tag ; skos:prefLabel "Weaviate" . tag:lm_search a sl:Tag ; skos:prefLabel "LM + Search" . tag:emnlp_2018 a sl:Tag ; skos:prefLabel "EMNLP 2018" . tag:sparse_retrieval a sl:Tag ; skos:prefLabel "Sparse retrieval" . dc:title "UKPLab/EasyNMT: Easy to use, state-of-the-art Neural Machine Translation for 100+ languages" ; sl:creationDate "2022-10-14" ; sl:tag tag:nils_reimers , tag:neural_machine_translation , tag:github_project . tag:langchain a sl:Tag ; skos:prefLabel "LangChain" . dc:title "stanfordnlp/dspy: 𝗗𝗦𝗣: Demonstrate-Search-Predict. A framework for composing retrieval and language models for knowledge-intensive NLP." ; sl:comment "(initially called DSP, rebranded as DSPy)\r\n\r\n> The DSP framework provides a programming abstraction for building grounded AI systems. In a few lines of code, a DSP program expresses rich interactions between retrieval models (RMs) and language models (LMs) to tackle difficult knowledge-intensive NLP tasks (e.g., complex question answering or conversational search).\r\n\r\n> DSP discourages [\"prompt engineering\"](tag:prompted_models), which we view much the same way as hyperparameter tuning in traditional ML\r\n\r\n[@matei_zaharia](https://twitter.com/matei_zaharia/status/1626705622585716737?s=20):\r\n>Who are the World Cup champions? I knew ChatGPT would get it wrong when it launched, but it's surprising that all the new search+LLM engines do too.\r\n>\r\n> **Combining retrieval+LMs won't just be a matter of prompting**. That's why we've been building tools like DSP at Stanford to do it. " ; sl:creationDate "2023-02-18" ; sl:tag tag:prompted_models , tag:lm_search , tag:github_project , tag:dsp_demonstrate_search_predict , tag:knowledge_intensive_nlp_tasks , tag:nlp_stanford , tag:retriever_reader , tag:nlp_based_ir , tag:omar_khattab . tag:doc_to_text a sl:Tag ; skos:prefLabel "doc-to-text" . dc:title "DerwenAI/kglab: an abstraction layer in Python for building knowledge graphs" ; sl:creationDate "2021-01-30" ; sl:tag tag:python_library , tag:knowledge_graph , tag:github_project . tag:imdb a sl:Tag ; skos:prefLabel "IMDB" . dc:title "Introducing FastBert — A simple Deep Learning library for BERT Models" ; sl:creationDate "2019-05-23" ; sl:tag tag:huggingface_transformers , tag:fast_ai , tag:bert . tag:bert a sl:Tag ; skos:prefLabel "BERT" . tag:kd_mkb_biblio a sl:Tag ; skos:prefLabel "KD-MKB biblio" . tag:kg_embeddings_library a sl:Tag ; skos:prefLabel "KG Embeddings Library" . tag:nlp_and_search a sl:Tag ; skos:prefLabel "NLP and Search" . tag:phrase_mining a sl:Tag ; skos:prefLabel "Phrase mining" . tag:azure_openai a sl:Tag ; skos:prefLabel "Azure OpenAI" . dc:title "mozilla/DeepSpeech: A TensorFlow implementation of Baidu's DeepSpeech architecture" ; sl:comment "open source Speech-To-Text engine" ; sl:creationDate "2019-12-10" ; sl:tag tag:speech_recognition , tag:github_project , tag:baidu . dc:title "raphaelsty/nlapi" ; sl:creationDate "2021-11-02" ; sl:tag tag:raphaelsty , tag:github_project . dc:title "ddangelov/Top2Vec: Top2Vec learns jointly embedded topic, document and word vectors." ; sl:comment "> Top2Vec is an algorithm for topic modeling and semantic search. It automatically detects topics present in text and generates jointly embedded topic, document and word vectors.\r\n>\r\n> \"Update: Pre-trained Universal Sentence Encoders and BERT Sentence Transformer now available for embedding.\"\r\n\r\n> **The assumption the algorithm makes is that many semantically similar documents are indicative of an underlying topic**. The first step is to create a joint embedding of document and word vectors. Once documents and words are embedded in a vector space the goal of the algorithm is to find dense clusters of documents, then identify which words attracted those documents together. Each dense area is a topic and the words that attracted the documents to the dense area are the topic words.\r\n\r\n> Once you train the Top2Vec model you can:\r\n> - ...\r\n> - Get **hierarchical topics**.\r\n> - Search topics by keywords.\r\n> - Search documents by topic, by keywords.\r\n> - Find similar words, similar documents.\r\n\r\nRefered by [BERTopic](doc:2022/03/maartengr_bertopic_leveraging_)" ; sl:creationDate "2022-03-10" ; sl:tag tag:top2vec , tag:github_project . tag:llm a sl:Tag ; skos:prefLabel "LLM" . tag:yves_peirsman a sl:Tag ; skos:prefLabel "Yves Peirsman" . dc:title "Aho-Corasick (java implementation)" ; sl:comment "Nowadays most free-text searching is based on Lucene-like approaches, where the search text is parsed into its various components. For every keyword a lookup is done to see where it occurs. When looking for a couple of keywords this approach is great. But what about it if you are not looking for just a couple of keywords, but a 100,000 of them? Like, for example, checking against a dictionary?\r\n\r\nThis is where the Aho-Corasick algorithm shines.\r\n" ; sl:creationDate "2019-04-24" ; sl:tag tag:github_project , tag:aho_corasick_algorithm . tag:benjamin_clavie a sl:Tag ; skos:prefLabel "Benjamin Clavié" . dc:title "Calculates Word Mover's Distance Insanely Fast" ; sl:creationDate "2017-11-12" ; sl:tag tag:word_mover_s_distance , tag:github_project . tag:howto a sl:Tag ; skos:prefLabel "Howto" . tag:graph_embeddings a sl:Tag ; skos:prefLabel "Graph Embeddings" . tag:nlp_juridique a sl:Tag ; skos:prefLabel "NLP + juridique" . dc:title "MaartenGr/BERTopic: Leveraging BERT and c-TF-IDF to create easily interpretable topics." ; sl:comment "> topic modeling technique that leverages 🤗 transformers and [c-TF-IDF](https://github.com/MaartenGr/cTFIDF) to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions.\r\n\r\nrefers to [Top2Vec](doc:2022/03/ddangelov_top2vec_top2vec_lear)\r\n\r\n[youtube](https://www.youtube.com/watch?v=Qub3PrFvauI)\r\n\r\n[tweet](https://twitter.com/JayAlammar/status/1594681648121102336?s=20&t=R0G_LrajK9WBtzypwXtD7Q)" ; sl:creationDate "2022-03-10" ; sl:tag tag:topic_modeling , tag:github_project , tag:bertopic , tag:bert . dc:title "raphaelsty/textokb: Extract knowledge from raw text" ; sl:comment "Implementation of [From Text to Knowledge: The Information Extraction Pipeline | by Tomaz Bratanic](doc:2021/08/from_text_to_knowledge_the_inf).\r\n> I added the [LUKE](doc:2020/11/2010_01057_luke_deep_context) model to predict relations between entities." ; sl:creationDate "2021-08-18" ; sl:tag tag:raphaelsty , tag:knowledge_extraction , tag:github_project . tag:adapter_modules_finetuning a sl:Tag ; skos:prefLabel "Adapter modules (LM finetuning)" . dc:title "Knowledge-base Extractor (github)" ; sl:comment "This is a node.js application that aims at extracting the knowledge represented in the Google infoboxes (aka Google Knowlege Graph Panel)" ; sl:creationDate "2014-05-29" ; sl:tag tag:node_js , tag:google_knowledge_graph , tag:github_project . tag:concept_extraction a sl:Tag ; skos:prefLabel "Concept Extraction / Linking" . tag:acl_2017 a sl:Tag ; skos:prefLabel "ACL 2017" . tag:max_halford a sl:Tag ; skos:prefLabel "Max Halford" . tag:reproducible_research a sl:Tag ; skos:prefLabel "Reproducible Research" . tag:llamaindex a sl:Tag ; skos:prefLabel "LlamaIndex" . tag:top2vec a sl:Tag ; skos:prefLabel "Top2Vec" . tag:sbert a sl:Tag ; skos:prefLabel "Sentence-BERT" . tag:nlp_facebook a sl:Tag ; skos:prefLabel "NLP@Facebook" . dc:title "Sylvain Gugger sur Twitter : \"Load any HuggingFace model in Int8 precision and save half the memory...\"" ; sl:comment "load_in_8bit=True Available on the main branch of Transformers" ; sl:creationDate "2022-08-11" ; sl:tag tag:tweet , tag:sylvain_gugger , tag:huggingface_transformers , tag:deep_learning_optimization_methods . tag:deep_learning_optimization_methods a sl:Tag ; skos:prefLabel "Deep Learning: Optimization methods" . dc:title "RDF2RDFa-izer" ; sl:comment "RDF2RDFa-izer is currently a deadly simple web frontend of the RDFa Serializer plugin (written by Keith Alexander) for ARC, a Semantic Web Framework written in PHP." ; sl:creationDate "2013-08-27" ; sl:tag tag:rdf_owl_documentation_tool , tag:rdf2rdfa , tag:github_project . dc:title "Azure-Samples/openai-python-enterprise-logging" ; sl:creationDate "2023-05-09" ; sl:tag tag:github_project , tag:azure_openai . tag:knowledge_intensive_nlp_tasks a sl:Tag ; skos:prefLabel "Knowledge-Intensive NLP Tasks" . tag:solid a sl:Tag ; skos:prefLabel "Solid" . dc:title "nicknochnack/LangchainDocuments: Leveraging Your Own Documents in a Langchain Pipeline" ; sl:comment "[youtube](https://www.youtube.com/watch?v=u8vQyTzNGVY&ab_channel=NicholasRenotte)" ; sl:creationDate "2023-05-14" ; sl:tag tag:youtube_video , tag:sample_code , tag:langchain , tag:github_project , tag:discute_avec_baptiste , tag:chatgpt_over_your_data . tag:knowledge_extraction a sl:Tag ; skos:prefLabel "Knowledge Extraction" . dc:title "RAKE: A python implementation of the Rapid Automatic Keyword Extraction" ; sl:creationDate "2017-06-26" ; sl:tag tag:rake , tag:python_nlp , tag:github_project . dc:title "raphaelsty/rebert: Renault Bert" ; sl:comment "MLM pre-training using an already pre-trained model, eg. continue the pre-training on Renault's texts\r\n\r\nInspired by [Retraining roberta-base using the RoBERTa MLM Procedure | Medium](doc:2022/03/retraining_roberta_base_using_t)" ; sl:creationDate "2021-07-26" ; sl:tag tag:raphaelsty , tag:github_project . tag:fast_ai a sl:Tag ; skos:prefLabel "fast.ai" . tag:chatgpt_retrieval_plugin a sl:Tag ; skos:prefLabel "ChatGPT Retrieval Plugin" . dc:title "raphaelsty/ckb: Contextual knowledge bases" ; sl:comment "Une implémentation de [BLP](tag:blp) [[2010.03496] Inductive Entity Representations from Text via Link Prediction](doc:2020/11/2010_03496_inductive_entity_r)" ; sl:creationDate "2020-11-09" ; sl:tag tag:semanlink_tag_finder , tag:raphaelsty , tag:github_project , tag:ckb . tag:dense_passage_retrieval a sl:Tag ; skos:prefLabel "Dense Passage Retrieval" . dc:title "ELS-RD/transformer-deploy: Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀" ; sl:creationDate "2022-06-13" ; sl:tag tag:onnx , tag:nlp_juridique , tag:ml_deploy , tag:huggingface_transformers , tag:github_project . dc:title "evilstreak/markdown-js" ; sl:creationDate "2015-10-11" ; sl:tag tag:evilstreak_markdown_js . tag:spiking_neural_network a sl:Tag ; skos:prefLabel "Spiking Neural Network" . tag:discussed_with_ns a sl:Tag ; skos:prefLabel "Discussed with NS" . tag:dsp_demonstrate_search_predict a sl:Tag ; skos:prefLabel "DSPy (Demonstrate-Search-Predict)" . dc:title "GitHub - OpenNMT/OpenNMT-py: Open Source Neural Machine Translation in PyTorch" ; sl:creationDate "2020-01-17" ; sl:tag tag:pytorch , tag:open_source , tag:neural_machine_translation , tag:github_project . tag:cool a sl:Tag ; skos:prefLabel "Cool" . dc:title "Carrot2: Text Clustering Algorithms and Applications" ; sl:comment "Open Source Search Results Clustering Engine. It can automatically organize small collections of documents (like, ehm, search results), into thematic categories." ; sl:creationDate "2017-05-23" ; sl:tag tag:github_project , tag:carrot2 . tag:relation_extraction a sl:Tag ; skos:prefLabel "Relation Extraction" . tag:baidu a sl:Tag ; skos:prefLabel "Baidu" . tag:onnx a sl:Tag ; skos:prefLabel "ONNX" . tag:carrot2 a sl:Tag ; skos:prefLabel "Carrot2" . dc:title "facebookresearch/fastText: Library for fast text representation and classification." ; sl:creationDate "2017-06-28" ; sl:tag tag:github_project , tag:fasttext . dc:title "GitHub - marcotcr/lime: Lime: Explaining the predictions of any machine learning classifier" ; sl:creationDate "2018-09-09" ; sl:tag tag:lime , tag:github_project . tag:setfit_sbert_fine_tuning a sl:Tag ; skos:prefLabel "SetFit (SBERT fine-tuning)" . dc:title "datquocnguyen/LFTM: Improving Topic Models with Latent Feature Word Representations (GitHub)" ; sl:creationDate "2017-05-22" ; sl:tag tag:topic_models_word_embedding , tag:github_project . tag:peinture a sl:Tag ; skos:prefLabel "Painting" . tag:python_nlp a sl:Tag ; skos:prefLabel "Python-NLP" . tag:word_mover_s_distance a sl:Tag ; skos:prefLabel "Word Mover’s Distance" . tag:knowledge_graph a sl:Tag ; skos:prefLabel "Knowledge Graphs" . tag:llm_kg a sl:Tag ; skos:prefLabel "LLM + KG" . tag:emnlp_2019 a sl:Tag ; skos:prefLabel "EMNLP 2019" . tag:jena_dev a sl:Tag ; skos:prefLabel "Jena dev" . dc:title "raphaelsty/kdmlm: Combine knowledge bases with language models." ; sl:creationDate "2021-02-16" ; sl:tag tag:these_renault_embeddings , tag:raphaelsty , tag:github_project . tag:document_processing a sl:Tag ; skos:prefLabel "Document AI" . dc:title "GitHub - anvaka/word2vec-graph: Exploring word2vec embeddings as a graph of nearest neighbors" ; sl:creationDate "2018-03-12" ; sl:tag tag:word2vec , tag:graph_visualization , tag:github_project . tag:olivier_grisel a sl:Tag ; skos:prefLabel "Olivier Grisel" . tag:clustering_of_text_documents a sl:Tag ; skos:prefLabel "Clustering of text documents" . tag:language_identification a sl:Tag ; skos:prefLabel "Language Identification" . dc:title "GitHub - solid/react-components at v1.4.0" ; sl:comment "Basic React components for building your own Solid components and apps" ; sl:creationDate "2019-03-02" ; sl:tag tag:solid , tag:ruben_verborgh , tag:react_js , tag:github_project . tag:kd_mkb a sl:Tag ; skos:prefLabel "KD-MKB" . tag:sentence_similarity a sl:Tag ; skos:prefLabel "Sentence Similarity" . tag:few_shot_learning a sl:Tag ; skos:prefLabel "Few-shot learning" . tag:continual_learning a sl:Tag ; skos:prefLabel "Continual Learning" . tag:chatbot a sl:Tag ; skos:prefLabel "Chatbots" . tag:facebook_fair a sl:Tag ; skos:prefLabel "Facebook FAIR" . tag:retrieval_augmented_generation a sl:Tag ; skos:prefLabel "RAG (Retrieval-Augmented Generation)" . dc:title "Retrieval Augmented Generation with Huggingface Transformers and Ray | Distributed Computing with Ray" ; sl:comment "> Huggingface Transformers recently added the Retrieval Augmented Generation (RAG) model, a new NLP architecture that leverages external documents (like Wikipedia) to augment its knowledge and achieve state of the art results on knowledge-intensive tasks\r\n\r\n[Hugging Face sur Twitter : \"Transformers release of the Retrieval-Augmented Generation model in collaboration with @facebookai!\"](doc:2021/02/hugging_face_sur_twitter_tra)" ; sl:creationDate "2021-02-11" ; sl:tag tag:retrieval_augmented_lm , tag:retrieval_augmented_generation , tag:huggingface_transformers . tag:keras a sl:Tag ; skos:prefLabel "Keras" . dc:title "ibiscp/LLM-IMDB: Proof of concept app using LangChain and LLMs to retrieve information from graphs, built with the IMDB dataset" ; sl:comment "> IMDB-LLM, a proof of concept app that demonstrates the power of LangChain and LLMs in extracting information from graphs!" ; sl:creationDate "2023-04-10" ; sl:tag tag:sample_code , tag:llm , tag:langchain , tag:imdb , tag:github_project . tag:angularjs a sl:Tag ; skos:prefLabel "AngularJS" . tag:ckb a sl:Tag ; skos:prefLabel "CKB" . tag:bert_and_sentence_embeddings a sl:Tag ; skos:prefLabel "BERT + Sentence Embeddings" . tag:nlp_sample_code a sl:Tag ; skos:prefLabel "NLP sample code" . tag:gpt_2 a sl:Tag ; skos:prefLabel "GPT-2" . dc:title "Transformers Pipelines.ipynb - Colaboratory" ; sl:comment "> One of the easiest ways to get started with neural networks is by loading pre-trained neural networks through the HuggingFace Transformers pipeline interface" ; sl:creationDate "2021-05-26" ; sl:tag tag:sample_code , tag:huggingface_transformers , tag:google_colab . tag:gpt_frugal_alternatives a sl:Tag ; skos:prefLabel "GPT: frugal alternatives" . tag:knowledge_distillation a sl:Tag ; skos:prefLabel "Knowledge distillation" . tag:discute_avec_baptiste a sl:Tag ; skos:prefLabel "Discuté avec Baptiste" . tag:layout_parser a sl:Tag ; skos:prefLabel "Layout-Parser" . dc:title "Keywords2vec" ; sl:comment "To generate a word2vec model, but using keywords instead of one word. Tokenize on stopwords + non word characters\r\n\r\n(This remembers me author of [FlashText algorithm](tag:flashtext_algorithm.html) saying he had developed it to create word2vec models)" ; sl:creationDate "2019-02-09" ; sl:tag tag:nlp_topic_extraction , tag:simple_idea , tag:github_project , tag:medical_ir_ml_ia , tag:rake , tag:phrase_mining , tag:word2vec . dc:title "kamalkraj/BERT-NER: Pytorch-Named-Entity-Recognition-with-BERT" ; sl:comment "Use google BERT to do CoNLL-2003 NER !" ; sl:creationDate "2021-02-07" ; sl:tag tag:named_entity_recognition , tag:github_project , tag:bert . tag:simple_idea a sl:Tag ; skos:prefLabel "Simple idea" . tag:intent_classification_and_slot_filling a sl:Tag ; skos:prefLabel "Intent classification and slot filling" . dc:title "BrunoRB/ahocorasick: Aho-corasick for javascript." ; sl:creationDate "2020-04-18" ; sl:tag tag:github_project , tag:aho_corasick_algorithm . dc:title "AmbiverseNLU: A Natural Language Understanding suite by Max Planck Institute for Informatics" ; sl:creationDate "2020-03-13" ; sl:tag tag:nlp_tools , tag:nlp_using_knowledge_graphs , tag:github_project , tag:entity_linking , tag:concept_extraction . dc:title "axa-group/Parsr: Transforms PDF, Documents and Images into Enriched Structured Data" ; sl:creationDate "2022-09-04" ; sl:tag tag:pdf_extract , tag:github_project , tag:axa . tag:elmo a sl:Tag ; skos:prefLabel "ELMo" . tag:gpt_alternatives a sl:Tag ; skos:prefLabel "GPT: alternatives" . tag:aho_corasick_algorithm a sl:Tag ; skos:prefLabel "Aho–Corasick algorithm" . tag:markdown a sl:Tag ; skos:prefLabel "Markdown" . tag:nearest_neighbor_search a sl:Tag ; skos:prefLabel "Nearest neighbor search" . tag:nlp_datasets a sl:Tag ; skos:prefLabel "NLP datasets" . dc:title "D2KLab/entity2rec: entity2rec generates item recommendation from knowledge graphs" ; sl:creationDate "2018-06-04" ; sl:tag tag:recommended_reading , tag:raphael_troncy , tag:knowledge_graph_embeddings , tag:github_project . tag:sigma_js a sl:Tag ; skos:prefLabel "Sigma.js" . tag:topic_models_word_embedding a sl:Tag ; skos:prefLabel "Topic Models + Word embedding" . dc:title "PaintTransformer - a Hugging Face Space by akhaliq" ; sl:comment "> Gradio demo for Paint Transformer: Feed Forward Neural Painting with Stroke Prediction." ; sl:creationDate "2021-08-11" ; sl:tag tag:peinture , tag:huggingface_transformers , tag:demo , tag:cool . dc:title "Finding similar documents with transformers · Codegram" ; sl:creationDate "2020-07-10" ; sl:tag tag:nlp_sample_code , tag:nlp_and_search , tag:identification_of_similar_documents , tag:huggingface_transformers , tag:faiss . tag:andrej_karpathy a sl:Tag ; skos:prefLabel "Andrej Karpathy" . dc:title "microsoft/semantic-kernel: Integrate cutting-edge LLM technology quickly and easily into your apps" ; sl:creationDate "2023-11-16" ; sl:tag tag:semantic_kernel . dc:title "raphaelsty/sparsembed: Sparse Information Retrieval with Transformers" ; sl:comment "> unofficial replication of the research papers: \r\n> - [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](doc:2023/05/2107_05720_splade_sparse_lex) \r\n> - [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](doc:2023/07/2109_10086_splade_v2_sparse_)\r\n> - [SparseEmbed: Learning Sparse Lexical Representations with Contextual Embeddings for Retrieval](doc:2023/07/sparseembed_learning_sparse_le)" ; sl:creationDate "2023-08-21" ; sl:tag tag:splade , tag:sparse_retrieval , tag:sparse_dense , tag:raphaelsty , tag:github_project . tag:bi_lstm a sl:Tag ; skos:prefLabel "bi-LSTM" . tag:named_entity_recognition a sl:Tag ; skos:prefLabel "Named Entity Recognition" . dc:title "markdown-it" ; sl:creationDate "2017-02-11" ; sl:tag tag:markdown_ittt , tag:github_project . tag:locality_sensitive_hashing a sl:Tag ; skos:prefLabel "Locality Sensitive Hashing" . tag:2d_nlp a sl:Tag ; skos:prefLabel "2D-NLP" . tag:nlp_stanford a sl:Tag ; skos:prefLabel "NLP@Stanford" . dc:title "Salmon Run: Word Sense Disambiguation using BERT as a Language Model" ; sl:creationDate "2020-12-01" ; sl:tag tag:word_sense_disambiguation , tag:nlp_sample_code , tag:huggingface_transformers , tag:bert . dc:title "IBM/zshot: Zero and Few shot named entity & relationships recognition" ; sl:creationDate "2022-12-23" ; sl:tag tag:spacy , tag:relation_extraction , tag:nlp_ibm , tag:named_entity_recognition , tag:github_project , tag:few_shot_learning . tag:tutorial a sl:Tag ; skos:prefLabel "Tutorial" . tag:francois_scharffe a sl:Tag ; skos:prefLabel "François Scharffe" . tag:word_embedding a sl:Tag ; skos:prefLabel "Word embeddings" . dc:title "Biterm Topic Model (github)" ; sl:creationDate "2017-06-07" ; sl:tag tag:github_project , tag:biterm_topic_model . dc:title "LAION-AI/Open-Assistant: OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so." ; sl:comment "Project's goal: A truly open ChatGPT like assistant" ; sl:creationDate "2023-02-06" ; sl:tag tag:github_project , tag:chatgpt . tag:arxiv_doc a sl:Tag ; skos:prefLabel "Arxiv Doc" . dc:title "facebookresearch/fairseq-py: Facebook AI Research Sequence-to-Sequence Toolkit written in Python." ; sl:creationDate "2017-10-02" ; sl:tag tag:sequence_to_sequence_learning , tag:python , tag:github_project , tag:facebook . tag:research_papers a sl:Tag ; skos:prefLabel "Research papers" . dc:title "iliaschalkidis/ELMo-keras: Re-implementation of ELMo on Keras" ; sl:comment "based on the tensorflow implementation presented by Allen NLP\r\n" ; sl:creationDate "2018-11-14" ; sl:tag tag:keras , tag:github_project , tag:elmo . dc:title "raphaelsty/neural-cherche: Neural Search" ; sl:comment "> a library to fine-tune neural search models such as Splade, ColBERT, and SparseEmbed on a specific dataset" ; sl:creationDate "2023-11-17" ; sl:tag tag:splade , tag:raphaelsty , tag:neural_models_for_information_retrieval , tag:github_project , tag:colbert , tag:cherche_raphael . dc:title "FastHugs | ntentional" ; sl:comment "Notebook: fine-tune a text classification model with HuggingFace transformers and fastai-v2." ; sl:creationDate "2020-02-19" ; sl:tag tag:nlp_text_classification , tag:nlp_sample_code , tag:huggingface_transformers , tag:fast_ai . tag:hugging_face a sl:Tag ; skos:prefLabel "Hugging Face" . tag:neural_models_for_information_retrieval a sl:Tag ; skos:prefLabel "Neural Search" . tag:emnlp_2021 a sl:Tag ; skos:prefLabel "EMNLP 2021" . dc:title "microsoft/semantic-kernel: Integrate cutting-edge LLM technology quickly and easily into your apps" ; sl:comment "> Semantic Kernel is an SDK that integrates Large Language Models (LLMs) like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C#, Python, and Java. Semantic Kernel achieves this by allowing you to define plugins that can be chained together... What makes Semantic Kernel special, however, is its ability to automatically orchestrate plugins with AI. With Semantic Kernel planners, you can ask an LLM to generate a plan that achieves a user's unique goal. Afterwards, Semantic Kernel will execute the plan for the user." ; sl:creationDate "2023-10-19" ; sl:tag tag:nlp_microsoft , tag:llm , tag:github_project . tag:word_sense_disambiguation a sl:Tag ; skos:prefLabel "Word-sense disambiguation" . dc:title "dmlc/dgl: Python package built to ease deep learning on graph, on top of existing DL frameworks." ; sl:comment "DGL is a Python package that interfaces between existing tensor libraries and data being expressed as graphs. It makes implementing graph neural networks (including Graph Convolution Networks, TreeLSTM, and many others) easy while maintaining high computation efficiency" ; sl:creationDate "2018-12-12" ; sl:tag tag:graph_neural_networks , tag:github_project . dc:title "jerryjliu/llama_index: LlamaIndex (GPT Index)" ; sl:comment "[Doc](doc:2023/04/welcome_to_llamaindex_🦙_gpt_i)\r\n> a project that provides a central interface to connect your LLM's with external data." ; sl:creationDate "2023-04-01" ; sl:tag tag:llamaindex , tag:gpt_alternatives , tag:github_project . dc:title "UKPLab/beir: A Heterogeneous Benchmark for Information Retrieval." ; sl:comment "> BEIR is a heterogeneous benchmark containing diverse IR tasks.\r\n> Easy to use, evaluate your NLP-based retrieval models across 15+ diverse IR datasets.\r\n\r\n[Paper](doc:2021/07/2104_08663_beir_a_heterogeno)" ; sl:creationDate "2021-07-09" ; sl:tag tag:github_project , tag:discussed_with_ns , tag:beir . dc:title "GitHub - kawine/usif: Implementation of unsupervised smoothed inverse frequency" ; sl:comment "Github project associated to [USIF paper](doc:?uri=http%3A%2F%2Fwww.aclweb.org%2Fanthology%2FW18-3012%2F)" ; sl:creationDate "2018-10-20" ; sl:tag tag:github_project . dc:title "Elasticsearch meets BERT: Building Search Engine with Elasticsearch and BERT" ; sl:comment "- Links to [this ES blog post](/doc/2020/01/text_similarity_search_in_elast)\r\n- [somewhat related](/doc/2020/01/building_a_search_engine_with_b)" ; sl:creationDate "2020-01-10" ; sl:tag tag:text_similarity , tag:nlp_and_search , tag:github_project , tag:elasticsearch , tag:bert . dc:title "zalandoresearch/flair: A very simple framework for state-of-the-art NLP" ; sl:comment "> A very simple framework for state-of-the-art NLP. Developed by Zalando Research.\r\n\r\npaper: [\"Contextual String Embeddings for Sequence Labeling (2018)\"](/doc/?uri=http%3A%2F%2Faclweb.org%2Fanthology%2FC18-1139)\r\n" ; sl:creationDate "2018-08-24" ; sl:tag tag:word_embedding , tag:sequence_labeling , tag:nlp_tools , tag:github_project , tag:flair . tag:parameter_efficient_fine_tuning_peft a sl:Tag ; skos:prefLabel "Parameter-efficient fine-tuning (PEFT)" . tag:semi_supervised_qa a sl:Tag ; skos:prefLabel "Semi-Supervised QA" . dc:title "jeshraghian/snntorch: Deep learning with spiking neural networks in Python" ; sl:comment "a Python package for performing gradient-based learning with spiking neural networks" ; sl:creationDate "2021-07-26" ; sl:tag tag:spiking_neural_network , tag:python , tag:github_project . dc:title "angular-jsonld" ; sl:comment "This angular module facilitates the integration of JSON-LD server APIs in AngularJS clients. It is implemented on top of Restagular. Its purpose is to provide an adapter layer to map client's data model to the server's API model by using the semantics embedded in JSON-LD as the contract interface. Another important functionality of angular-jsonld is to enable easy navigation of JSON-LD hyperlinks in client's code." ; sl:creationDate "2015-08-29" ; sl:tag tag:json_ld , tag:github_project , tag:angularjs . tag:domain_specific_bert a sl:Tag ; skos:prefLabel "Domain-Specific BERT" . tag:alpaca a sl:Tag ; skos:prefLabel "Alpaca" . dc:title "A collection of notebooks for Natural Language Processing from NLP Town" ; sl:creationDate "2019-02-07" ; sl:tag tag:yves_peirsman , tag:nlp_sample_code , tag:github_project . tag:d3js a sl:Tag ; skos:prefLabel "D3js" . tag:tensorflow a sl:Tag ; skos:prefLabel "TensorFlow" . tag:fine_tuning a sl:Tag ; skos:prefLabel "Fine-tuning" . dc:title "huggingface/text-clustering: Easily embed, cluster and semantically label text datasets" ; sl:comment "tools to easily embed and cluster texts as well as label clusters semantically" ; sl:creationDate "2024-03-07" ; sl:tag tag:hugging_face , tag:github_project , tag:clustering_of_text_documents . tag:demo a sl:Tag ; skos:prefLabel "Demo" . dc:title "[1908.10084] Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks" ; sl:comment "> Sentence-BERT\r\n(SBERT), a modification of the pretrained\r\nBERT network that use siamese and triplet network\r\nstructures to derive **semantically meaningful\r\nsentence embeddings** that can be compared\r\nusing cosine-similarity.\r\n\r\nImportant because \r\n\r\n- BERT ist unsuitable for semantic similarity\r\nsearch as well as for unsupervised tasks\r\nlike clustering.\r\n- simple methods such as using the CLS token give low quality sentence embeddings\r\n\r\nHowever, the purpose of SBERT sentence embeddings\r\nare **not to be used for transfer learning for other\r\ntasks**.\r\n\r\n[Related blog post](/doc/2020/01/richer_sentence_embeddings_usin); [Github](https://github.com/UKPLab/sentence-transformers)" ; sl:creationDate "2019-08-28" ; sl:tag tag:huggingface_transformers , tag:nearest_neighbor_search , tag:emnlp_2019 , tag:arxiv_doc , tag:sentence_similarity , tag:siamese_network , tag:sbert . dc:title "ATerm library on GitHub" ; sl:creationDate "2015-04-13" ; sl:tag tag:github_project , tag:aterm . tag:hydra a sl:Tag ; skos:prefLabel "Hydra" . tag:identification_of_similar_documents a sl:Tag ; skos:prefLabel "Identification of similar documents" . dc:title "Nils Reimers sur Twitter : EasyNMT Easy-to-use (3 lines of code), state-of-the-art neural machine translations" ; sl:creationDate "2021-04-27" ; sl:tag tag:tweet , tag:nils_reimers , tag:neural_machine_translation , tag:huggingface_transformers . dc:title "fozziethebeat/S-Space - Java - GitHub" ; sl:comment "a collection of algorithms for building Semantic Spaces. Semantics space algorithms capture the statistical regularities of words in a text corpora and map each word to a high-dimensional vector that represents the semantics." ; sl:creationDate "2016-01-18" ; sl:tag tag:nlp_tools , tag:github_project . dc:title "fonnesbeck/ScipySuperpack @ GitHub" ; sl:comment "A script for building the Python scientific stack on OS X" ; sl:creationDate "2014-07-16" ; sl:tag tag:python , tag:github_project . tag:spacy a sl:Tag ; skos:prefLabel "spaCy" . tag:nlp_using_knowledge_graphs a sl:Tag ; skos:prefLabel "Knowledge Graphs in NLP" . tag:zero_shot_text_classifier a sl:Tag ; skos:prefLabel "Zero-shot Text Classifier" . tag:rdflib a sl:Tag ; skos:prefLabel "RDFLib" . dc:title "A Benchmark of Text Classification in PyTorch" ; sl:creationDate "2018-02-28" ; sl:tag tag:nlp_text_classification , tag:pytorch , tag:python_sample_code , tag:nlp_sample_code , tag:github_project , tag:benchmark . tag:semanlink_tag_finder a sl:Tag ; skos:prefLabel "Semanlink Tag Finder" . dc:title "princeton-nlp/DensePhrases" ; sl:comment "> DensePhrases is a text retrieval model that can return phrases, sentences, passages, or documents for your natural language inputs. Using billions of dense phrase vectors from the entire Wikipedia, DensePhrases searches phrase-level answers to your questions in real-time or retrieves passages for downstream tasks.\r\n\r\ncf.:\r\n- ACL'2021: Learning Dense Representations of Phrases at Scale; \r\n- EMNLP'2021: [Phrase Retrieval Learns Passage Retrieval, Too](doc:2021/09/2109_08133_phrase_retrieval_l)\r\n" ; sl:creationDate "2021-09-30" ; sl:tag tag:nlp_princeton , tag:github_project , tag:emnlp_2021 , tag:dense_passage_retrieval , tag:acl_2021 . tag:acl_2020 a sl:Tag ; skos:prefLabel "ACL 2020" . tag:pdf_extract a sl:Tag ; skos:prefLabel "http://www.semanlink.net/tag/pdf_extract" . tag:persistent_data_structure a sl:Tag ; skos:prefLabel "Persistent data structure" . dc:title "ATOM, a hackable text editor for the 21st Century" ; sl:creationDate "2014-09-09" ; sl:tag tag:atom_github . tag:stanford_pos_tagger a sl:Tag ; skos:prefLabel "Stanford POS Tagger" . dc:title "raphaelsty/cherche: Neural search" ; sl:comment "> Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers. Cherche is meant to be used with small to medium sized corpora." ; sl:creationDate "2022-01-11" ; sl:tag tag:raphaelsty , tag:neural_models_for_information_retrieval , tag:github_project , tag:cherche_raphael . dc:title "Fastai with Transformers (BERT, RoBERTa, XLNet, XLM, DistilBERT)" ; sl:comment "integrates HuggingFace into fastai" ; sl:creationDate "2019-11-30" ; sl:tag tag:attention_is_all_you_need , tag:huggingface_transformers , tag:hugging_face , tag:fast_ai . dc:title "DataChazGPT sur Twitter : \"The new 𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛𝚜.𝚝𝚘𝚘𝚕𝚜 library from @huggingface is insane! E.g. you can summarize and chat with a PDF in just 6 lines of code...\"" ; sl:comment "using [textract](doc:2023/05/deanmalmgren_textract_extract_)" ; sl:creationDate "2023-05-14" ; sl:tag tag:tweet , tag:open_source , tag:huggingface_transformers , tag:discute_avec_baptiste , tag:pdf_chat . tag:nlp_microsoft a sl:Tag ; skos:prefLabel "NLP@Microsoft" . dc:title "PyTorch-BigGraph: Faster embeddings of large graphs - Facebook Code" ; sl:comment "> A new tool from Facebook AI Research that enables training of multi-relation graph embeddings for very large graphs. PyTorch-BigGraph (PBG) handles graphs with billions of nodes and trillions of edges. Since PBG is written in PyTorch, researchers and engineers can easily swap in their own loss functions, models, and other components.\r\n\r\n[Github](https://github.com/facebookresearch/PyTorch-BigGraph), [Blog post](https://ai.facebook.com/blog/open-sourcing-pytorch-biggraph-for-faster-embeddings-of-extremely-large-graphs)" ; sl:creationDate "2019-05-12" ; sl:tag tag:pytorch , tag:graph_embeddings , tag:github_project , tag:facebook_fair . tag:not_encoding_knowledge_in_language_model a sl:Tag ; skos:prefLabel "Not Encoding Factual Knowledge in Language Model" . dc:title "clem 🤗 sur Twitter : \"Llama 2 by @Meta is already integrated with @huggingface transformers, TGI, inference endpoints, PEFT and much more...\"" ; sl:creationDate "2023-07-19" ; sl:tag tag:tweet , tag:parameter_efficient_fine_tuning_peft , tag:llama_2 , tag:huggingface_transformers . tag:wikipedia a sl:Tag ; skos:prefLabel "Wikipedia" . tag:flair a sl:Tag ; skos:prefLabel "Flair" . tag:axa a sl:Tag ; skos:prefLabel "AXA" . dc:title "awslabs/unsupervised-qa: Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering" ; sl:comment "Code and synthetic data from our [ACL 2020 paper](doc:2022/02/2004_11892_template_based_que)\r\n\r\n> We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sentence improves downstream QA performance by allowing the model to learn more complex context-question relationships. " ; sl:creationDate "2021-12-08" ; sl:tag tag:unsupervised_qa , tag:synthetic_qa_data , tag:nlp_amazon , tag:github_project , tag:discussed_with_ns , tag:acl_2020 . tag:camembert_nlp a sl:Tag ; skos:prefLabel "CamemBERT" . dc:title "FasterXML/jackson-databind" ; sl:comment "The general-purpose data-binding functionality and tree-model for Jackson Data Processor. It builds on core streaming parser/generator package, and uses Jackson Annotations for configuration. " ; sl:creationDate "2015-03-10" ; sl:tag tag:jackson , tag:github_project . tag:graph_visualization a sl:Tag ; skos:prefLabel "Graph visualization" . tag:nn_tips a sl:Tag ; skos:prefLabel "NN tips" . tag:fasttext a sl:Tag ; skos:prefLabel "FastText" . tag:k_nearest_neighbors_algorithm a sl:Tag ; skos:prefLabel "k-nearest neighbors" . tag:category_embedding a sl:Tag ; skos:prefLabel "Category Embedding" . dc:title "How to to integrate Linkurious.js into Angular.js" ; sl:creationDate "2015-08-29" ; sl:tag tag:sigma_js , tag:github_project , tag:angularjs . dc:title "New pipeline for zero-shot text classification - 🤗Transformers - Hugging Face Forums" ; sl:comment "Same author: [Zero-shot classifier distillation at master · huggingface/transformers](doc:2021/02/zero_shot_classifier_distillati)" ; sl:creationDate "2021-03-15" ; sl:tag tag:zero_shot , tag:nlp_text_classification , tag:huggingface_transformers . tag:vector_database a sl:Tag ; skos:prefLabel "Vector database" . dc:title "pyenv/pyenv: Simple Python version management" ; sl:creationDate "2023-05-11" ; sl:tag tag:pyenv , tag:github_project . tag:bertopic a sl:Tag ; skos:prefLabel "BERTopic" . tag:neo4j a sl:Tag ; skos:prefLabel "Neo4j" . dc:title "openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin" ; sl:comment "> The ChatGPT Retrieval Plugin lets you easily search and find personal or work documents by asking questions in everyday language.\r\n\r\n> uses OpenAI's text-embedding-ada-002 embeddings model to generate embeddings of document chunks, and then stores and queries them using a vector database on the backend. As an open-source and self-hosted solution, developers can deploy their own Retrieval Plugin and register it with ChatGPT. The Retrieval Plugin supports several vector database providers, allowing developers to choose their preferred one from a list.\r\n\r\n> Memory Feature; capacity to provide ChatGPT with memory. " ; sl:creationDate "2023-04-13" ; sl:tag tag:github_project , tag:chatgpt_retrieval_plugin . dc:title "deanmalmgren/textract: extract text from any document." ; sl:creationDate "2023-05-14" ; sl:tag tag:github_project , tag:doc_to_text . dc:title "Hugging Face sur Twitter : \"Transformers release of the Retrieval-Augmented Generation model in collaboration with @facebookai!\"" ; sl:comment "> the **RAG model is trained end-to-end for retrieval-in-the-loop generation**, a new paradigm that allows a model to go find useful information in a text corpus when generating.\r\n\r\n**No need to try to encode all of that knowledge in a trillion parameters any more ;)**" ; sl:creationDate "2021-02-23" ; sl:tag tag:tweet , tag:retrieval_augmented_lm , tag:retrieval_augmented_generation , tag:not_encoding_knowledge_in_language_model , tag:nlp_facebook , tag:huggingface_transformers . tag:openai_gpt a sl:Tag ; skos:prefLabel "OpenAI GPT" . tag:pyenv a sl:Tag ; skos:prefLabel "pyenv" . dc:title "allenai/macaw: Multi-angle c(q)uestion answering" ; sl:comment ">ready-to-use model capable of general question answering, showing robustness outside the domains it was trained on. It has been trained in \"multi-angle\" fashion, which means it can handle a flexible set of input and output \"slots\" (like question, answer, explanation) ." ; sl:creationDate "2022-01-22" ; sl:tag tag:question_answering , tag:github_project , tag:allennlp . tag:elasticsearch a sl:Tag ; skos:prefLabel "ElasticSearch" . tag:lm_adaptation_to_domain a sl:Tag ; skos:prefLabel "Language Model: domain adaptation" . dc:title "tristan/jsonld-java · GitHub" ; sl:creationDate "2012-08-14" ; sl:tag tag:json_ld , tag:github_project . tag:graph_neural_networks a sl:Tag ; skos:prefLabel "Graph neural networks" . tag:raphaelsty a sl:Tag ; skos:prefLabel "Raphaël Sourty" . dc:title "Retraining roberta-base using the RoBERTa MLM Procedure | Medium" ; sl:creationDate "2022-03-18" ; sl:tag tag:mlm , tag:lm_adaptation_to_domain , tag:huggingface_transformers , tag:howto . dc:title "GitHub - neo4j/NaLLM: Repository for the NaLLM project" ; sl:comment "> synergies between Neo4j and Large Language Models (LLMs). As a part of our ongoing project, we are focusing on three primary use cases: \r\n> - a Natural Language Interface to a Knowledge Graph, \r\n> - Creating a Knowledge Graph from Unstructured Data \r\n> - and Generate a Report using both static data and data from LLM." ; sl:creationDate "2023-08-14" ; sl:tag tag:neo4j , tag:llm_kg , tag:github_project . tag:prompted_models a sl:Tag ; skos:prefLabel "Prompting/In-context learning" . tag:word2vec a sl:Tag ; skos:prefLabel "Word2vec" .