# Modeling Topical Relevance for Multi-Turn Dialogue Generation

arXiv: https://arxiv.org/abs/2009.12735 · HTML: https://mlsanity.com/paper/2009.12735/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2020.

## Built on by (most cited first, 15 of 15)

- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach](https://mlsanity.com/paper/2102.10242/) (2021)
- [Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection](https://mlsanity.com/paper/2105.09509/) (2021)
- [Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning](https://mlsanity.com/paper/2205.02355/) (2022)
- [Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation](https://mlsanity.com/paper/2305.02747/) (2023)
- [MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation](https://mlsanity.com/paper/2208.08629/) (2022)
- [Decoupled Federated Learning for ASR with Non-IID Data](https://mlsanity.com/paper/2206.09102/) (2022)
- [Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order](https://mlsanity.com/paper/2301.00867/) (2023)
- [Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest](https://mlsanity.com/paper/2208.13472/) (2022)
- [Improving Topic Segmentation by Injecting Discourse Dependencies](https://mlsanity.com/paper/2209.08626/) (2022)
- [Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access](https://mlsanity.com/paper/2212.05373/) (2022)
- [Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text](https://mlsanity.com/paper/2109.02289/) (2021)
- [From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification](https://mlsanity.com/paper/2411.14252/) (2024)
- [Multi-Scale Feature and Metric Learning for Relation Extraction](https://mlsanity.com/paper/2107.13425/) (2021)
- [Contrast with Major Classifier Vectors for Federated Medical Relation Extraction with Heterogeneous Label Distribution](https://mlsanity.com/paper/2301.05376/) (2023)

## Abstract (arXiv)

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations.