Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension
This study considers the task of machine reading at scale (MRS) wherein, given a question, a system first performs the information retrieval (IR) task of finding relevant passages in a knowledge source and then carries out the reading comprehension (RC) task of extracting an answer span from the passages. Previous MRS studies, in which the IR component was trained without considering answer spans, struggled to accurately find a small number of relevant passages from a large set of passages. In this paper, we propose a simple and effective approach that incorporates the IR and RC tasks by using supervised multi-task learning in order that the IR component can be trained by considering answer spans. Experimental results on the standard benchmark, answering SQuAD questions using the full Wikipedia as the knowledge source, showed that our model achieved state-of-the-art performance. Moreover, we thoroughly evaluated the individual contributions of our model components with our new Japanese dataset and SQuAD. The results showed significant improvements in the IR task and provided a new perspective on IR for RC: it is effective to teach which part of the passage answers the question rather than to give only a relevance score to the whole passage.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalMulti-Task LearningReading ComprehensionRetrievalSimilar Papers 제목 키워드 기반
Query Rewriting for Retrieval-Augmented Large Language Models
Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read inste…
Language ModelingLanguage ModellingMultiple-choiceRetrieval+1Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given input document and then link the mentions t…
Entity LinkingEntity RetrievalKnowledge GraphsMachine Reading Comprehension+2End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieva…
Answer GenerationOpen-Domain Question AnsweringQuestion AnsweringRetrievalOptimizing Retrieval-augmented Reader Models via Token Elimination
Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as question answering, fact checking, etc. In FiD, supporting passages are first retrieved an…
Answer GenerationDecoderFact CheckingLanguage Modeling+3Generator-Retriever-Generator Approach for Open-Domain Question Answering
Open-domain question answering (QA) tasks usually require the retrieval of relevant information from a large corpus to generate accurate answers. We propose a novel approach called Generator-Retriever-Generator (GRG) tha…
Language ModelingLanguage ModellingLarge Language ModelOpen-Domain Question Answering+3