Knowledge-Aided Open-Domain Question Answering

Abstract

Open-domain question answering (QA) aims to find the answer to a question from a large collection of documents.Though many models for single-document machine comprehension have achieved strong performance, there is still much room for improving open-domain QA systems since document retrieval and answer reranking are still unsatisfactory. Golden documents that contain the correct answers may not be correctly scored by the retrieval component, and the correct answers that have been extracted may be wrongly ranked after other candidate answers by the reranking component. One of the reasons is derived from the independent principle in which each candidate document (or answer) is scored independently without considering its relationship to other documents (or answers). In this work, we propose a knowledge-aided open-domain QA (KAQA) method which targets at improving relevant document retrieval and candidate answer reranking by considering the relationship between a question and the documents (termed as question-document graph), and the relationship between candidate documents (termed as document-document graph). The graphs are built using knowledge triples from external knowledge resources. During document retrieval, a candidate document is scored by considering its relationship to the question and other documents. During answer reranking, a candidate answer is reranked using not only its own context but also the clues from other documents. The experimental results show that our proposed method improves document retrieval and answer reranking, and thereby enhances the overall performance of open-domain question answering.

References in corpus (15)

• A simple neural network module for relational reasoning
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• Quasar: Datasets for Question Answering by Search and Reading
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
• Efficient and Robust Question Answering from Minimal Context over Documents
• Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
• Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
• Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
• Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension
• Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension