# A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation

arXiv: https://arxiv.org/abs/1806.07000 · HTML: https://mlsanity.com/paper/1806.07000/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2018.

## Built on by (most cited first, 11 of 11)

- [Towards an Online Empathetic Chatbot with Emotion Causes](https://mlsanity.com/paper/2105.11903/) (2021)
- [TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge](https://mlsanity.com/paper/2203.08517/) (2022)
- [Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge](https://mlsanity.com/paper/2109.03004/) (2021)
- [Empathetic Dialog Generation with Fine-Grained Intents](https://mlsanity.com/paper/2105.06829/) (2021)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication](https://mlsanity.com/paper/2502.08896/) (2025)
- [Actionable Conversational Quality Indicators for Improving Task-Oriented Dialog Systems](https://mlsanity.com/paper/2109.11064/) (2021)
- [A Unified Framework for Emotion Identification and Generation in Dialogues](https://mlsanity.com/paper/2205.15513/) (2022)
- [Modeling Content-Emotion Duality via Disentanglement for Empathetic Conversation](https://mlsanity.com/paper/2209.12495/) (2022)
- [Survey of Design Paradigms for Social Robots](https://mlsanity.com/paper/2407.20556/) (2024)
- [Spiral Language Modeling](https://mlsanity.com/paper/2112.10543/) (2021)

## Abstract (arXiv)

Traditional neural language models tend to generate generic replies with poor logic and no emotion. In this paper, a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation (E-SCBA) is proposed to address this issue. In our model, pre-generated emotion keywords and topic keywords are asynchronously introduced into the process of decoding. It is much different from most existing methods which generate replies from the first word to the last. Through experiments, the results indicate that our approach not only improves the diversity of replies, but gains a boost on both logic and emotion compared with baselines.