Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

Abstract

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article. Our goals are to boost coverage by using knowledge-guided retrieval to find more relevant passages than text-matching methods, and to improve accuracy by allowing for better knowledge-guided fusion of information across related passages. Our graph retrieval method expands a set of seed keyword-retrieved passages by traversing the graph structure of the knowledge base. Our reader extends a BERT-based architecture and updates passage representations by propagating information from related passages and their relations, instead of reading each passage in isolation. Experiments on three open-domain QA datasets, WebQuestions, Natural Questions and TriviaQA, show improved performance over non-graph baselines by 2-11% absolute. Our approach also matches or exceeds the state-of-the-art in every case, without using an expensive end-to-end training regime.

References in corpus (6)

• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• End-to-End Open-Domain Question Answering with BERTserini
• A BERT Baseline for the Natural Questions
• Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
• Dynamic Integration of Background Knowledge in Neural NLU Systems
• Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Cited by in corpus (25)

• REALM: Retrieval-Augmented Language Model Pre-Training
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• Sparse, Dense, and Attentional Representations for Text Retrieval
• RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
• NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
• On the Effectiveness of Transfer Learning for Code Search
• Generation-Augmented Retrieval for Open-domain Question Answering
• Is Retriever Merely an Approximator of Reader?
• A Survey of Knowledge Enhanced Pre-trained Models
• Contextualized Representations Using Textual Encyclopedic Knowledge
• AmbigQA: Answering Ambiguous Open-domain Questions
• Attention-guided Generative Models for Extractive Question Answering
• Fusing Context Into Knowledge Graph for Commonsense Question Answering
• RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering
• A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering
• Retrieval Augmentation Reduces Hallucination in Conversation
• Iterative Hierarchical Attention for Answering Complex Questions over Long Documents
• Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources
• Open Question Answering over Tables and Text
• Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering
• Answering Any-hop Open-domain Questions with Iterative Document Reranking
• Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
• Relation-Guided Pre-Training for Open-Domain Question Answering
• Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories
• DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization