# Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs

arXiv: https://arxiv.org/abs/1709.04005 · HTML: https://mlsanity.com/paper/1709.04005/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2017.

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

- [PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation](https://mlsanity.com/paper/2109.09519/) (2021)
- [MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding](https://mlsanity.com/paper/2106.01541/) (2021)
- [LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming](https://mlsanity.com/paper/2306.08401/) (2023)
- [HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations](https://mlsanity.com/paper/2203.08500/) (2022)
- [Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2109.04066/) (2021)
- [Is ChatGPT a Good Multi-Party Conversation Solver?](https://mlsanity.com/paper/2310.16301/) (2023)
- [GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding](https://mlsanity.com/paper/2305.09360/) (2023)
- [Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations](https://mlsanity.com/paper/2409.18602/) (2024)
- [EM Pre-training for Multi-party Dialogue Response Generation](https://mlsanity.com/paper/2305.12412/) (2023)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation](https://mlsanity.com/paper/2412.05342/) (2024)
- [Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks](https://mlsanity.com/paper/2105.10323/) (2021)
- [What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study](https://mlsanity.com/paper/2109.09105/) (2021)
- [MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation](https://mlsanity.com/paper/2305.12733/) (2023)
- [Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization](https://mlsanity.com/paper/2305.12927/) (2023)
- [SS-MPC: A Sequence-Structured Multi-Party Conversation System](https://mlsanity.com/paper/2502.16920/) (2025)
- [GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant](https://mlsanity.com/paper/2603.01059/) (2026)
- [MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation](https://mlsanity.com/paper/2609.36903/) (2026)
- [Multi-party Response Generation with Relation Disentanglement](https://mlsanity.com/paper/2403.10827/) (2024)
- [MPCEval: A Benchmark for Multi-Party Conversation Generation](https://mlsanity.com/paper/2603.04969/) (2026)
- [On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels](https://mlsanity.com/paper/2607.15648/) (2026)

## Abstract (arXiv)

In this paper, we study the problem of addressee and response selection in multi-party conversations. Understanding multi-party conversations is challenging because of complex speaker interactions: multiple speakers exchange messages with each other, playing different roles (sender, addressee, observer), and these roles vary across turns. To tackle this challenge, we propose the Speaker Interaction Recurrent Neural Network (SI-RNN). Whereas the previous state-of-the-art system updated speaker embeddings only for the sender, SI-RNN uses a novel dialog encoder to update speaker embeddings in a role-sensitive way. Additionally, unlike the previous work that selected the addressee and response separately, SI-RNN selects them jointly by viewing the task as a sequence prediction problem. Experimental results show that SI-RNN significantly improves the accuracy of addressee and response selection, particularly in complex conversations with many speakers and responses to distant messages many turns in the past.