Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

Abstract

The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL. Furthermore, query languages can answer questions that require complex reasoning, as well as offering full explainability. In this paper, we propose a hybrid framework that takes both textual and tabular evidence as input and generates either direct answers or SQL queries depending on which form could better answer the question. The generated SQL queries can then be executed on the associated databases to obtain the final answers. To the best of our knowledge, this is the first paper that applies Text2SQL to ODQA tasks. Empirically, we demonstrate that on several ODQA datasets, the hybrid methods consistently outperforms the baseline models that only take homogeneous input by a large margin. Specifically we achieve state-of-the-art performance on OpenSQuAD dataset using a T5-base model. In a detailed analysis, we demonstrate that the being able to generate structural SQL queries can always bring gains, especially for those questions that requires complex reasoning.

15 pages, LaTeX; typos corrected, add the open source code link; published to ACL 2021

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• TAPAS: Weakly Supervised Table Parsing via Pre-training
• End-to-End Open-Domain Question Answering with BERTserini
• Passage Re-ranking with BERT
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
• Neural Programmer: Inducing Latent Programs with Gradient Descent
• X-SQL: reinforce schema representation with context
• Hybrid Ranking Network for Text-to-SQL
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• Content Enhanced BERT-based Text-to-SQL Generation
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
• Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
• Dataset for a Neural Natural Language Interface for Databases (NNLIDB)