Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
arXiv:1909.07598
Abstract
Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to `\emph{hop}' to other relevant evidence. In a setting, with more than \textbf{5 million} Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the \hotpot benchmark by \textbf{10.59} F1.
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Passage Re-ranking with BERT
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
- Word-Entity Duet Representations for Document Ranking
- DeepType: Multilingual Entity Linking by Neural Type System Evolution
- Investigating the Successes and Failures of BERT for Passage Re-Ranking
- A Deep Look into Neural Ranking Models for Information Retrieval
Cited by in corpus (10)
- Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
- Multi-hop Question Answering via Reasoning Chains
- Hierarchical Graph Network for Multi-hop Question Answering
- Knowledge-Aided Open-Domain Question Answering
- AutoKG: Constructing Virtual Knowledge Graphs from Unstructured Documents for Question Answering
- Answering Any-hop Open-domain Questions with Iterative Document Reranking
- Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games
- Complementary Evidence Identification in Open-Domain Question Answering
- Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
- Adaptive Information Seeking for Open-Domain Question Answering