]> > put some sunflower seeds in your pockets so that at least when you fall in battle some sunflowers will grow where you lie 2022-02-28T13:40:22Z 2022-02-28 StrictlyChristo🇺🇦 sur Twitter : "Ukrainian woman confronts Russian soldiers, calls them fascists and urges them to put some sunflower seeds in their pockets et aussi la sécheresse. Sur fond de lobbying russe pour le nucléaire 2022-02-03T00:12:55Z Derrière la panne géante d’électricité qui a paralysé l’Asie centrale, un système vétuste et les cryptomonnaies 2022-02-03 Nils Reimers sur Twitter : "Creating intent classes for chatbots is challenging This tutorial shows how to use sentence-transformers to find potentially overlapping intent classes and how to improve your data annotation work." / Twitter 2022-02-19T22:55:07Z 2022-02-19 Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering [2004.11892] Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering Ramesh Nallapati Patrick Ng 2020-04-24T17:57:45Z Zhiguo Wang [Gihub](doc:2021/12/awslabs_unsupervised_qa_templa) > we expand upon the recently introduced task of unsupervised question answering ([Lewis et al., 2019, Unsupervised Question Answering by Cloze Translation](doc:2021/12/1906_04980_unsupervised_quest)) to examine the extent to which synthetic training data alone can be used to train a QA model. focus on extractive, **factoid QA, where answers are named entities** -> focus on creating a relevant question from a (context, answer) pair in an unsupervised manner > We improve over [Lewis et al, 2019] by proposing a simple, intuitive, retrieval and template-based question generation approach > > Question Generation Pipeline: the original context sentence containing a given answer is used as a query to retrieve a related sentence containing matching entities, which is input into our question-style converter to create QA training data. 2004.11892 2020-04-24T17:57:45Z Alexander R. Fabbri Alexander R. Fabbri Question Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has been to fine-tune a pretrained language model on a task-specific labeled dataset. This paradigm, however, relies on scarce, and costly to obtain, large-scale human-labeled data. 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. Training a QA model on this data gives a relative improvement over a previous unsupervised model in F1 score on the SQuAD dataset by about 14%, and 20% when the answer is a named entity, achieving state-of-the-art performance on SQuAD for unsupervised QA. 2022-02-11 2022-02-11T14:06:18Z Bing Xiang 2022-02-18 > Python script to semantically cluster keywords in over one hundred languages using deep learning natural language processing cf. [sentence-transformers/fast_clustering.py](doc:2022/02/sentence_transformers_fast_clus) [Tweet](https://twitter.com/LeeFootSEO/status/1494297107607470081?s=20&t=HVAWKLMg2-QCEl6AhoBeuQ) Semantic Keyword Clustering For 10,000+ Keywords [With Script] 2022-02-18T14:46:46Z > This is a more complex example on performing clustering on large scale dataset. This examples find in a large set of sentences local communities, i.e., groups of sentences that are highly similar. You can freely configure the threshold what is considered as similar. A high threshold will only find extremely similar sentences, a lower threshold will find more sentence that are less similar. A second parameter is 'min_community_size': Only communities with at least a certain number of sentences will be returned. The method for finding the communities is extremely fast, for clustering 50k sentences it requires only 5 seconds (plus embedding comuptation). In this example, we download a large set of questions from Quora and then find similar questions in this set. 2022-02-18T14:45:22Z sentence-transformers/fast_clustering.py at master · UKPLab/sentence-transformers 2022-02-18 Thylacine (loup de Tasmanie) 2022-02-24T15:52:18Z 2022-02-24 > sentence-level, context-aware, and linguistically informed extractive search system. 2022-02-22 2022-02-22T01:33:42Z SPIKE: Extractive Search from Allen Institute for AI Clustering millions of sentences to optimize the ML-workflow 2022-02-19T10:37:15Z 2022-02-19 Nils Reimers sur Twitter : "how to use the fast clustering algorithm from sentence-transformers..." Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration Shufan Wang [2109.06304] Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration Laure Thompson 2021-09-13T20:31:57Z 2021-10-13T20:35:24Z 2109.06304 Mohit Iyyer 2022-02-25 Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-level similarity tasks, while also demonstrating increased lexical diversity between nearest neighbors in the vector space. Finally, as a case study, we show that Phrase-BERT embeddings can be easily integrated with a simple autoencoder to build a phrase-based neural topic model that interprets topics as mixtures of words and phrases by performing a nearest neighbor search in the embedding space. Crowdsourced evaluations demonstrate that this phrase-based topic model produces more coherent and meaningful topics than baseline word and phrase-level topic models, further validating the utility of Phrase-BERT. 2022-02-25T17:19:37Z Shufan Wang 2022-02-19T09:37:15Z 2022-02-19 L’appel de 1 600 archéologues à Roselyne Bachelot : « Ne coupez pas les vivres à l’archéologie programmée ! » 2022-02-03 2022-02-03T15:33:19Z Incidents à la centrale nucléaire du Tricastin : le lanceur d’alerte avait été reçu en secret par le gouvernement Exterminate All the Brutes (2021 film) 2022-02-02 2022-02-02T00:21:28Z Exterminez toutes ces brutes The Quick Guide to SQuAD 2022-02-03 2022-02-03T18:22:21Z Yosi Shamay sur Twitter : "a new platform for rapid ad-hoc knowledgebase construction using extractive search...." > a fully functional human-machine hybrid tool for rapid construction of knowledgebases (KB) in biomedicine. [Tweet](https://twitter.com/yoavgo/status/1495868946393800715) de [Yoav Goldberg](tag:yoav_goldberg) > This means that now we have a protocol, and a supporting toolset, by which researchers can create personalized, ad-hoc knowledge-basses in their fields of expertise, or in a field they want to get into, in hours. This is a great productivity boost to science. > How do you construct a KB with ES? > > 1. choose a topic. > 2. define a set of allowed relations between entity classes. > 3. extract entities+relations with the powerful NLP extraction engine-SPIKE. > 4. Import relations to the app and annotate/edit 2022-02-22T01:06:24Z 2022-02-22 Le Conseil constitutionnel freine l’exploitation de la mine Montagne d’or en Guyane 2022-02-18 2022-02-18T12:23:30Z 2022-02-06T01:23:19Z 2022-02-06 Part-of-Speech(POS) Tag | Dependency Parsing | Constituency Parsing SPIKE for Knowledge Base Construction a platform for knowledge base construction based on the SPIKE extractive search engine 2022-02-22T01:13:46Z 2022-02-22 2022-02-16 2022-02-16T23:01:03Z NLP: POS (Part of speech) Tagging & Chunking | by Suneel Patel | Medium 2022-02-28T13:31:09Z Why Vladimir Putin has already lost this war | Yuval Noah Harari | The Guardian 2022-02-28 2022-02-02 2022-02-02T21:38:33Z Svelte • Cybernetically enhanced web apps La Puissance et la Gloire — Wikipédia 2022-02-16 2022-02-16T00:10:55Z