Conversational Question Answering on Heterogeneous Sources

2022/04/25 by Philipp Christmann, Christmann, Philipp, Rishiraj Saha Roy +3 · 5 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2204.11677

openalex publication_date 2022/04/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text corpus, or a collection of tables. This paper addresses the novel issue of jointly tapping into all of these together, this way boosting answer coverage and confidence. We present CONVINSE, an end-to-end pipeline for ConvQA over heterogeneous sources, operating in three stages: i) learning an explicit structured representation of an incoming question and its conversational context, ii) harnessing this frame-like representation to uniformly capture relevant evidences from KB, text, and tables, and iii) running a fusion-in-decoder model to generate the answer. We construct and release the first benchmark, ConvMix, for ConvQA over heterogeneous sources, comprising 3000 real-user conversations with 16000 questions, along with entity annotations, completed question utterances, and question paraphrases. Experiments demonstrate the viability and advantages of our method, compared to state-of-the-art baselines.

Cited by

• SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
• Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs
• SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
• Towards Adaptive Context Management for Intelligent Conversational Question Answering
• Improving Document Retrieval Coherence for Semantically Equivalent Queries

Related

• Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
• CoQA: A Conversational Question Answering Challenge
• Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks
• A Survey of the State-of-the-Art in Conversational Question Answering Systems
• End-to-end Spoken Conversational Question Answering: Task, Dataset and Model