Semanlink - Technical girls and guys ; Deep Learning AND Knowledge-augmented Language Models

Printer friendly

Search Tag:

Search Doc:

Preferences...

Tag Cloud

ACL - Arxiv Doc - Benjamin Clavié - Cheat sheet - Dan Jurafsky - Discuté avec M. Labeau - Discuté avec Raphaël - DSPy (Demonstrate-Search-Predict) - EMNLP 2021 - Generalization - GitHub project - Hard negative mining - J'y étais - Knowledge-augmented Language Models - Knowledge distillation - Knowledge Extraction - Knowledge-Intensive NLP Tasks - LangChain - Language Models + Knowledge - LlamaIndex - LM + Search - LM evaluation - Memory in deep learning - Michael Glass - Named Entity Recognition - NLP@Facebook - NLP@IBM - NLP@Stanford - NLP based IR - Node2Vec - Not Encoding Factual Knowledge in Language Model - Olivier Ferret - Omar Khattab - Open-source LLM - Prompting/In-context learning - Prompts - Question Answering - RAG (Retrieval-Augmented Generation) - RAGatouille - Retrieval augmented LM - Retriever-Reader - Sample code - Slot filling - Transformers - Tweet - Webinar - YouTube video - Zero shot -

Technical girls and guys ; Deep Learning AND Knowledge-augmented Language Models

Common descendants

DSPy (Demonstrate-Search-Predict)

19 Documents

Tags:

2024-04-12 About

Leonie sur X : "Ollama allows you to run open source LLMs LOCALLY..."

Tags:

2024-03-30 About

DSPy Cheatsheet | DSPy

Tags:

2024-03-30 About

Krista Opsahl-Ong sur X : "Got a pipeline with **multiple prompts**, like a DSPy program? ... Introducing MIPRO, a Multi-prompt Instruction Proposal Optimizer...."

Tags:

2024-03-09 About

Intro to DSPy: Goodbye Prompting, Hello Programming! | by Leonie Monigatti | Feb, 2024 | Towards Data Science

Tags:

DSPy (Demonstrate-Search-Predict)

2024-03-01 About

bclavie/RAGatouille

Tags:

2024-01-26 About

Omar Khattab sur X : "...Let's use 30 lines of DSPy—without any hand-written prompts or any calls to OpenAI ($0)—to teach..."

Tags:

2024-01-01 About

Specializing Static and Contextual Embeddings in the Medical Domain Using Knowledge Graphs: Let’s Keep It Simple - ACL Anthology (2022)

Tags:

2023-10-11 About

Inside DSPy: The New Language Model Programming Framework You Need… – Towards AI

Tags:

DSPy (Demonstrate-Search-Predict)

2023-09-06 About

Omar Khattab sur X : "Announcing 𝗗𝗦𝗣y..."

Tags:

2023-08-24 About

[2212.14024] Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP

Tags:

2023-06-23 About

Jerry Liu sur Twitter : "The DSP project carries a lot of insights for improving RAG..."

Tags:

2023-06-18 About

LangChain Retrieval Webinar - YouTube

Tags:

2023-05-27 About

Jerry Liu sur Twitter : "To evaluate retrieval-augmented LLM’s, we can compare the query/response/source context to see if they match. We just added this to @gpt_index..."

Tags:

2023-04-11 About

stanfordnlp/dspy: 𝗗𝗦𝗣: Demonstrate-Search-Predict. A framework for composing retrieval and language models for knowledge-intensive NLP.

Tags:

2023-02-18 About

[2207.06300] Re2G: Retrieve, Rerank, Generate

Tags:

2022-07-14 About

[2108.13934] Robust Retrieval Augmented Generation for Zero-shot Slot Filling

Tags:

2022-01-19 About

[1911.00172] Generalization through Memorization: Nearest Neighbor Language Models

Tags:

2019-12-20 About

[1909.04120] Span Selection Pre-training for Question Answering

Tags:

> a **new pre-training task inspired by reading
comprehension** and an **effort to avoid encoding general knowledge in the transformer network itself**

Current transformer architectures store general knowledge -> large models, long pre-training time. Better to offload the requirement of general knowledge to a sparsely activated network.

"Span selection" as an additional auxiliary task: the query is a sentence drawn from a corpus
with a term replaced with a special token: [BLANK]. The term replaced by the blank is the answer term. The passage is
relevant as determined by a BM25 search, and answer-bearing (containing the answer
term). Unlike BERT’s cloze task, where the answer must be drawn from the model itself, the answer is found in a passage
using language understanding.

> **We hope to progress to a model of general purpose language modeling that uses an indexed long
term memory to retrieve world knowledge, rather than holding it in the densely activated transformer encoder layers.**

2019-09-18 About