# An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss

arXiv: https://arxiv.org/abs/1811.07078 · HTML: https://mlsanity.com/paper/1811.07078/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2018.

## Built on by (most cited first, 21 of 21)

- [Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought](https://mlsanity.com/paper/2401.06836/) (2024)
- [A Literature Survey of Recent Advances in Chatbots](https://mlsanity.com/paper/2201.06657/) (2022)
- [CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI](https://mlsanity.com/paper/2205.14727/) (2022)
- [Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum](https://mlsanity.com/paper/2312.06441/) (2023)
- [Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection](https://mlsanity.com/paper/2210.11715/) (2022)
- [KECRS: Towards Knowledge-Enriched Conversational Recommendation System](https://mlsanity.com/paper/2105.08261/) (2021)
- [Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation](https://mlsanity.com/paper/2301.04907/) (2023)
- [Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality](https://mlsanity.com/paper/2110.04614/) (2021)
- [Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation](https://mlsanity.com/paper/2205.09314/) (2022)
- [Empathetic Dialog Generation with Fine-Grained Intents](https://mlsanity.com/paper/2105.06829/) (2021)
- [Self-Emotion Blended Dialogue Generation in Social Simulation Agents](https://mlsanity.com/paper/2408.01633/) (2024)
- [CTSM: Combining Trait and State Emotions for Empathetic Response Model](https://mlsanity.com/paper/2403.15516/) (2024)
- [DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines](https://mlsanity.com/paper/2212.10557/) (2022)
- [A Review of Affective Generation Models](https://mlsanity.com/paper/2202.10763/) (2022)
- [WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue](https://mlsanity.com/paper/2108.01487/) (2021)
- [CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective](https://mlsanity.com/paper/2205.03540/) (2022)
- [Towards Multi-Turn Empathetic Dialogs with Positive Emotion Elicitation](https://mlsanity.com/paper/2204.10509/) (2022)
- [A Unified Framework for Emotion Identification and Generation in Dialogues](https://mlsanity.com/paper/2205.15513/) (2022)
- [Conversation Derailment Forecasting with Graph Convolutional Networks](https://mlsanity.com/paper/2306.12982/) (2023)
- [Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image Data](https://mlsanity.com/paper/2402.07640/) (2024)
- [K-Quantization and its Impact on Output Performance](https://mlsanity.com/paper/2605.19645/) (2026)

## Abstract (arXiv)

Affect conveys important implicit information in human communication. Having the capability to correctly express affect during human-machine conversations is one of the major milestones in artificial intelligence. In recent years, extensive research on open-domain neural conversational models has been conducted. However, embedding affect into such models is still under explored. In this paper, we propose an end-to-end affect-rich open-domain neural conversational model that produces responses not only appropriate in syntax and semantics, but also with rich affect. Our model extends the Seq2Seq model and adopts VAD (Valence, Arousal and Dominance) affective notations to embed each word with affects. In addition, our model considers the effect of negators and intensifiers via a novel affective attention mechanism, which biases attention towards affect-rich words in input sentences. Lastly, we train our model with an affect-incorporated objective function to encourage the generation of affect-rich words in the output responses. Evaluations based on both perplexity and human evaluations show that our model outperforms the state-of-the-art baseline model of comparable size in producing natural and affect-rich responses.