Improve Dense Passage Retrieval with Entailment Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dai, Lu, Liu, Hao, Xiong, Hui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914981666095104
author Dai, Lu
Liu, Hao
Xiong, Hui
author_facet Dai, Lu
Liu, Hao
Xiong, Hui
contents Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query and passage pairs. However, the definition of relevance is often ambiguous. We observed that a major class of relevance aligns with the concept of entailment in NLI tasks. Based on this observation, we designed a method called entailment tuning to improve the embedding of dense retrievers. Specifically, we unify the form of retrieval data and NLI data using existence claim as a bridge. Then, we train retrievers to predict the claims entailed in a passage with a variant task of masked prediction. Our method can be efficiently plugged into current dense retrieval methods, and experiments show the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15801
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improve Dense Passage Retrieval with Entailment Tuning
Dai, Lu
Liu, Hao
Xiong, Hui
Computation and Language
Information Retrieval
Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query and passage pairs. However, the definition of relevance is often ambiguous. We observed that a major class of relevance aligns with the concept of entailment in NLI tasks. Based on this observation, we designed a method called entailment tuning to improve the embedding of dense retrievers. Specifically, we unify the form of retrieval data and NLI data using existence claim as a bridge. Then, we train retrievers to predict the claims entailed in a passage with a variant task of masked prediction. Our method can be efficiently plugged into current dense retrieval methods, and experiments show the effectiveness of our method.
title Improve Dense Passage Retrieval with Entailment Tuning
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2410.15801