Abstract
Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these. However, conversational question-answering remains challenging due to the lack of realistic, domain-specific training data. Inspired by this bottleneck, we focus on conversational question generation as a means to generate synthetic conversations for training and evaluation purposes. We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. Specifically, we design ChainCQG as a two-stage architecture that learns question-answer representations across multiple dialogue turns using a flow propagation training strategy. ChainCQG significantly outperforms both answer-aware and answer-unaware SOTA baselines (e.g., up to 48% BLEU-1 improvement). Additionally, our model is able to generate different types of questions, with improved fluidity and coreference alignment.- Anthology ID:
- 2021.eacl-main.177
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2061–2070
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.177
- DOI:
- 10.18653/v1/2021.eacl-main.177
- Cite (ACL):
- Jing Gu, Mostafa Mirshekari, Zhou Yu, and Aaron Sisto. 2021. ChainCQG: Flow-Aware Conversational Question Generation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2061–2070, Online. Association for Computational Linguistics.
- Cite (Informal):
- ChainCQG: Flow-Aware Conversational Question Generation (Gu et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2021.eacl-main.177.pdf
- Code
- searchableai/ChainCQG
- Data
- CoQA