Open-Domain Dialogue Generation Based on Pre-trained Language Models

2020/10/24 by Yan Zeng, Jian-Yun Nie, Zeng, Yan +2
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.2010.12780

[v0], 10 pages, 4 figures

arxiv created 2020/10/24 · openalex publication_date 2020/10/24 · arxiv updated 2020/10/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Pre-trained language models have been successfully used in response generation for open-domain dialogue. Four main frameworks have been proposed: (1) Transformer-ED using Transformer encoder and decoder separately for source and target sentences; (2) Transformer-Dec using Transformer decoder for both source and target sentences; (3) Transformer-MLM using Transformer decoder that applies bi-directional attention on the source side and left-to-right attention on the target side with masked language model objective; and (4) Transformer-AR that uses auto-regressive objective instead. In this study, we compare these frameworks on 3 datasets, and our comparison reveals that the best framework uses bidirectional attention on the source side and does not separate encoder and decoder. We also examine model discrepancy, and our experiments confirm that the performance of a model is directly impacted by the underlying discrepancies. We then propose two correction methods to reduce the discrepancies, and both improve the model performance. These results show that discrepancies is an important factor to consider when we use a pre-trained model, and a reduction in discrepancies can lead to improved performance.

Citations

• A Neural Conversational Model
• A Coefficient of Agreement for Nominal Scales
• Generating Wikipedia by Summarizing Long Sequences
• A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data
• Towards a Human-like Open-Domain Chatbot
• UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
• Multi-Domain Dialogue State Tracking based on State Graph

Related

• An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation
• Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialogue
• Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
• Promoting Open-domain Dialogue Generation through Learning Pattern Information between Contexts and Responses
• Pretrained Language Models for Dialogue Generation with Multiple Input Sources