# Assigning personality/identity to a chatting machine for coherent conversation generation

arXiv: https://arxiv.org/abs/1706.02861 · HTML: https://mlsanity.com/paper/1706.02861/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2017.

## Built on by (most cited first, 10 of 10)

- [Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction](https://mlsanity.com/paper/2106.03044/) (2021)
- [Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function](https://mlsanity.com/paper/2303.13797/) (2023)
- [Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks](https://mlsanity.com/paper/2105.10323/) (2021)
- [Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation](https://mlsanity.com/paper/2502.11423/) (2025)
- [Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learning](https://mlsanity.com/paper/2205.11206/) (2022)
- [PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona](https://mlsanity.com/paper/2504.17390/) (2025)
- [Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation](https://mlsanity.com/paper/2107.07771/) (2021)
- [Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona](https://mlsanity.com/paper/2109.08875/) (2021)
- [Heterogeneous-Branch Collaborative Learning for Dialogue Generation](https://mlsanity.com/paper/2303.11621/) (2023)
- [Android Security using NLP Techniques: A Review](https://mlsanity.com/paper/2107.03072/) (2021)

## Abstract (arXiv)

Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations. In this paper, we address the issue of generating responses that are coherent to a pre-specified agent profile. We design a model consisting of three modules: a profile detector to decide whether a post should be responded using the profile and which key should be addressed, a bidirectional decoder to generate responses forward and backward starting from a selected profile value, and a position detector that predicts a word position from which decoding should start given a selected profile value. We show that general conversation data from social media can be used to generate profile-coherent responses. Manual and automatic evaluation shows that our model can deliver more coherent, natural, and diversified responses.