<Retrieval> [DPR] Dense Passage Retrieval for Open-Domain Question Answering (2020.04)

<Retrieval> [DPR] Dense Passage Retrieval for Open-Domain Question Answering (2020.04)

관심있는 NLP 논문을 읽어보고 간단히 정리했습니다. (Language & Knowledge Lab의 Retreival 관련) 혹시 부족하거나 잘못된 내용이 있다면 댓글 부탁드립니다 ️ [Facebook AI, University of Washington, Princeton University] - dense representation을 사용하여 효과적으로 implemented될 수 있다. - 적은 숫자의 question과 passage로 학습된 embedding과 simple dual-encoder framework 배경 Open-Domain Question Answering (ODQA) 문제를 풀기 위해 (1) context retriever (2) machine reader를 사용하는 two-..

원문링크 : <Retrieval> [DPR] Dense Passage Retrieval for Open-Domain Question Answering (2020.04)

 등록된 다른 글

<CoT, Prompting> [Google DeepMind] Chain-of-Thought Reasoning Without Prompting (2024.02)

<CoT, Prompting> [Google DeepMind] Chain-of-Thought Reasoning Without Prompting (2024.02)

파이썬 정규표현식 연습(비밀번호 패턴, html 태그 제거)

파이썬 정규표현식 연습(비밀번호 패턴, html 태그 제거)

<Retrieval, In-Context Learning> RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models

<Retrieval, In-Context Learning> RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models

Python and Vectorization(1)

Python and Vectorization(1)

[Paper Review] BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding

[Paper Review] BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding

<LLM> Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models (2024.02)

<LLM> Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models (2024.02)

<Prompting, Decomposition> Least-to-Most Prompting Enables Complex Reasoning in Large Language Models (2023.04)

<Prompting, Decomposition> Least-to-Most Prompting Enables Complex Reasoning in Large Language Models (2023.04)

Analysis of Algorithms(4) : Order-of-Growth Classifications

Analysis of Algorithms(4) : Order-of-Growth Classifications