<LK Lab, Retrieval> [Np Decoding] Nonparametric Decoding for Generative Retrieval (2023.05)

<LK Lab, Retrieval> [Np Decoding] Nonparametric Decoding for Generative Retrieval (2023.05)

관심있는 NLP 논문을 읽어보고 간단히 정리했습니다. (Language & Knowledge Lab의 Retreival 관련) 혹시 부족하거나 잘못된 내용이 있다면 댓글 부탁드립니다 ️ [KAIST AI, Kakao] - 현존하는 generative retrieval model에 모두 적용 가능한 Nonparametric Decoding (Np Decoding)을 제안 - Np Decoding은 nonparametric contextualized vocab embedding (external memory)를 사용 배경 Text Retrieval에서 bi-encoder를 사용하는 방식은 embedding space bottleneck과 large storage space 문제가 존재 최근 인기를 끌고..

원문링크 : <LK Lab, Retrieval> [Np Decoding] Nonparametric Decoding for Generative Retrieval (2023.05)

 등록된 다른 글

[프로그래머스] 연속된 부분 수열의 합 (Python)

[프로그래머스] 연속된 부분 수열의 합 (Python)

<LLM, Zero-shot> [T0] Multitask Prompted Training Enables Zero-Shot Task Generalization (2022.03)

<LLM, Zero-shot> [T0] Multitask Prompted Training Enables Zero-Shot Task Generalization (2022.03)

[Short Paper Review] We're Afraid Language Models Aren't Modeling Ambiguity

[Short Paper Review] We're Afraid Language Models Aren't Modeling Ambiguity

<NLP> [Transformer] Attention Is All You Need (2017.06)

<NLP> [Transformer] Attention Is All You Need (2017.06)

<CoT> [Self-Consistency] Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022.03 -> 2023.03)

<CoT> [Self-Consistency] Self-Consistency Improves Chain of Thought Reasoning in Language Models (2022.03 -> 2023.03)

Building AI in Your Company(2)

Building AI in Your Company(2)

[BOJ] 11053 : 가장 긴 증가하는 부분 수열 [DP](Python)

[BOJ] 11053 : 가장 긴 증가하는 부분 수열 [DP](Python)

[BOJ] 9019 : DSLR [DFS/BFS](Python)

[BOJ] 9019 : DSLR [DFS/BFS](Python)