# BERT with History Answer Embedding for Conversational Question Answering

**Authors:** Chen Qu, Liu Yang, Minghui Qiu, W. Bruce Croft, Yongfeng Zhang, Mohit Iyyer  
**arXiv:** [1905.05412](https://arxiv.org/abs/1905.05412)  
**Date:** 2019-05-14  
**Summary page:** https://www.summarizepaper.com/en/paper/1905.05412v1/

## Key points

- The paper proposes a new approach to multi-turn conversational search by modeling conversation history to answer current questions.
- Existing methods either prepend history turns or use complicated attention mechanisms to model the history, which can be challenging.
- The proposed approach is called "history answer embedding" and enables seamless integration of conversation history into a ConvQA model built on BERT.
- ConvQA is seen as a simplified but concrete setting of conversational search, and the authors provide a general framework to solve it.
- The effectiveness of the approach is demonstrated under this framework, and different numbers of history turns are analyzed for their impact on conversation history modeling in ConvQA.
- The study was conducted by Chen Qu, Liu Yang, Minghui Qiu, W. Bruce Croft, Yongfeng Zhang, and Mohit Iyyer and has been accepted as a short paper at SIGIR 2019.

## Summary

The paper titled "BERT with History Answer Embedding for Conversational Question Answering" proposes a novel approach to multi-turn conversational search by modeling the conversation history to answer the current question. The authors highlight that existing methods either prepend history turns to the current question or use complicated attention mechanisms to model the history, which can be challenging. To address this, they propose a conceptually simple yet highly effective approach called history answer embedding that enables seamless integration of conversation history into a conversational question answering (ConvQA) model built on BERT. The authors explain their view that ConvQA is a simplified but concrete setting of conversational search and provide a general framework to solve it. They further demonstrate the effectiveness of their approach under this framework and analyze the impact of different numbers of history turns under different settings to provide new insights into conversation history modeling in ConvQA. The study was conducted by Chen Qu, Liu Yang, Minghui Qiu, W. Bruce Croft, Yongfeng Zhang, and Mohit Iyyer and has been accepted as a short paper at SIGIR 2019.