BERT with History Answer Embedding for Conversational Question Answering

Abstract

Conversational search is an emerging topic in the information retrieval community. One of the major challenges to multi-turn conversational search is to model the conversation history to answer the current question. Existing methods either prepend history turns to the current question or use complicated attention mechanisms to model the history. We propose a conceptually simple yet highly effective approach referred to as history answer embedding. It enables seamless integration of conversation history into a conversational question answering (ConvQA) model built on BERT (Bidirectional Encoder Representations from Transformers). We first explain our view that ConvQA is a simplified but concrete setting of conversational search, and then we provide a general framework to solve ConvQA. We further demonstrate the effectiveness of our approach under this framework. Finally, we analyze the impact of different numbers of history turns under different settings to provide new insights into conversation history modeling in ConvQA.

Accepted to SIGIR 2019 as a short paper

References in corpus (3)

• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Analyzing and Characterizing User Intent in Information-seeking Conversations
• User Intent Prediction in Information-seeking Conversations

Cited by in corpus (11)

• Open-Retrieval Conversational Question Answering
• Exploring the State of the Art in Legal QA Systems
• Natural Language Understanding with Privacy-Preserving BERT
• PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models
• Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search
• Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension
• A Dataset for Sentence Retrieval for Open-Ended Dialogues
• Open-domain question classification and completion in conversational information search
• A Pairwise Probe for Understanding BERT Fine-Tuning on Machine Reading Comprehension
• Towards Adaptive Context Management for Intelligent Conversational Question Answering
• One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning