mlsanityData to 7 Oct 2026

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

arXiv 2410.20766 ↗First posted 28 Oct 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history, rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this paper, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 28 Oct 2024.

Builds on

27 of 49 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  6. 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
  7. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  8. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  9. 2016A Persona-Based Neural Conversation Modelcited by 221
  10. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  11. 2015A Neural Conversational Modelcited by 195
  12. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
15 more
  1. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  2. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  3. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  4. 2017Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Modelscited by 42
  5. 2017Hierarchical Recurrent Attention Network for Response Generationcited by 34
  6. 2019ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generationcited by 32
  7. 2018Retrieval-Enhanced Adversarial Training for Neural Response Generationcited by 22
  8. 2017Neural Personalized Response Generation as Domain Adaptationcited by 19
  9. 2019Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variablescited by 19
  10. 2016Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generationcited by 16
  11. 2017A Conditional Variational Framework for Dialog Generationcited by 16
  12. 2019Unsupervised Context Rewriting for Open Domain Conversationcited by 14
  13. 2019Generating Diverse Translation by Manipulating Multi-Head Attentioncited by 14
  14. 2019When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generationcited by 3
  15. 2016Learning to Start for Sequence to Sequence Architecturecited by 1

Built on by

Not cited yet.