mlsanityData to 7 Oct 2026

Incorporating Causal Analysis into Diversified and Logical Response Generation

arXiv 2209.09482 ↗First posted 20 Sep 2022cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Although the Conditional Variational AutoEncoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical with the question. A causal analysis is carried out to study the reasons behind, and a methodology of searching for the mediators and mitigating the confounding bias in dialogues is provided. Specifically, we propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediators into generating process. Besides, a dynamic topic graph guided conditional variational autoencoder (TGG-CVAE) model is utilized to complement the semantic space and reduce the confounding bias in responses. Extensive experiments demonstrate that the proposed model is able to generate both relevant and informative responses, and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 20 Sep 2022.

Builds on

30 of 51 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  7. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  8. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  9. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  10. 2020A Survey on Causal Inferencecited by 202
  11. 2015A Neural Conversational Modelcited by 195
  12. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
18 more
  1. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  2. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  3. 2020Interventional Few-Shot Learningcited by 112
  4. 2021Causal Attention for Vision-Language Taskscited by 111
  5. 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
  6. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  7. 2021Graph Infomax Adversarial Learning for Treatment Effect Estimation with Networked Observational Datacited by 42
  8. 2016Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversationcited by 35
  9. 2020Matching in Selective and Balanced Representation Space for Treatment Effects Estimationcited by 30
  10. 2021Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interactioncited by 21
  11. 2019A Discrete CVAE for Response Generation on Short-Text Conversationcited by 17
  12. 2018Generating Multiple Diverse Responses for Short-Text Conversationcited by 13
  13. 2020Target Guided Emotion Aware Chat Machinecited by 10
  14. 2022Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Datacited by 9
  15. 2019Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selectioncited by 8
  16. 2022Multi-Task Adversarial Learning for Treatment Effect Estimation in Basket Trialscited by 6
  17. 2022Hierarchical Capsule Prediction Network for Marketing Campaigns Effectcited by 5
  18. 2018Another Diversity-Promoting Objective Function for Neural Dialogue Generationcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2024A Causal Explainable Guardrails for Large Language Modelscited by 18
  2. 2024Personalized Topic Selection Model for Topic-Grounded Dialoguecited by 1
  3. 2023Continual Causal Effect Estimation: Challenges and Opportunitiescited by 0
  4. 2024Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialoguecited by 0