BERT with History Answer Embedding for Conversational Question Answering
This work addresses the problem of conversational search for information retrieval practitioners, offering an incremental but effective solution for history modeling.
The authors tackled the challenge of modeling conversation history in multi-turn conversational question answering by proposing a simple history answer embedding method integrated with BERT, achieving strong performance with concrete improvements over baselines.
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.