paper-with-me

홈 › Papers

Diversifying Neural Dialogue Generation via Negative Distillation

2022-05-05 · NAACL 2022 7 · Yiwei Li, Shaoxiong Feng, Bin Sun, Kan Li

Generative dialogue models suffer badly from the generic response problem, limiting their applications to a few toy scenarios. Recently, an interesting approach, namely negative training, has been proposed to alleviate this problem by reminding the model not to generate high-frequency responses during training. However, its performance is hindered by two issues, ignoring low-frequency but generic responses and bringing low-frequency but meaningless responses. In this paper, we propose a novel negative training paradigm, called negative distillation, to keep the model away from the undesirable generic responses while avoiding the above problems. First, we introduce a negative teacher model that can produce query-wise generic responses, and then the student model is required to maximize the distance with multi-level negative knowledge. Empirical results show that our method outperforms previous negative training methods significantly.

📄 PDF Abstract BibTeX arXiv:2205.02795

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue Generation

Similar Papers 제목 키워드 기반

Diversifying Neural Dialogue Generation via Negative Distillation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Generative dialogue models suffer from serious generic response problems, limiting their applications to a few toy scenarios. Recently, an interesting approach, namely negative training, has been proposed to alleviate t…

Dialogue Generation

Heterogeneous-Branch Collaborative Learning for Dialogue Generation

2023-03-21 · Yiwei Li, Shaoxiong Feng, Bin Sun, Kan Li

With the development of deep learning, advanced dialogue generation methods usually require a greater amount of computational resources. One promising approach to obtaining a high-performance and lightweight model is kno…

AttributeDialogue GenerationKnowledge Distillation

Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation

2021-03-02 · Yu Cao, Liang Ding, Zhiliang Tian, Meng Fang

Dialogue generation models face the challenge of producing generic and repetitive responses. Unlike previous augmentation methods that mostly focus on token manipulation and ignore the essential variety within a single s…

Dialogue GenerationDiversity

Diversifying Dialogue Generation with Non-Conversational Text

2020-05-09 · ACL 2020 6 · Hui Su, Xiaoyu Shen, Sanqiang Zhao, Xiao Zhou 외

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency d…

Dialogue GenerationDiversityTranslation

Diversifying Dialog Generation via Adaptive Label Smoothing

2021-05-30 · ACL 2021 5 · Yida Wang, Yinhe Zheng, Yong Jiang, Minlie Huang

Neural dialogue generation models trained with the one-hot target distribution suffer from the over-confidence issue, which leads to poor generation diversity as widely reported in the literature. Although existing appro…

DecoderDialogue GenerationDiversity