Share This Author
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization
This work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task.
Group-wise Contrastive Learning for Neural Dialogue Generation
This work introduces contrastive learning into dialogue generation, where the model explicitly perceives the difference between the well-chosen positive and negative utterances, and augments contrastive dialogue learning with group-wise dual sampling.
Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition
- Haolan Zhan, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Yongjun Bao, Yanyan Lan
- Computer ScienceNAACL
- 1 June 2021
A sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data.
CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation
Experimental results on two widely-used knowledge-grounded dialogue datasets show that the proposed collaborative latent variable (CoLV) model outperforms previous methods on both knowledge selection and response generation.
Regularizing Dialogue Generation by Imitating Implicit Scenarios
- Shaoxiong Feng, Xuancheng Ren, Hongshen Chen, Bin Sun, Kan Li, Xu Sun
- Computer ScienceEMNLP
- 5 October 2020
This work proposes to improve generative dialogue systems from the scenario perspective, where both dialogue history and future conversation are taken into account to implicitly reconstruct the scenario knowledge.
Improving Sequential Recommendation Consistency with Self-Supervised Imitation
A model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation is proposed and experiments show that SSI effectively outperforms the state-of-the-art sequential recommendation methods.
Collaborative Group Learning
- Shaoxiong Feng, Hongshen Chen, Xuancheng Ren, Zhuoye Ding, Kan Li, Xu Sun
- Computer ScienceAAAI
- 16 September 2020
Empirical evaluations indicate that the proposed Collaborative Group Learning method significantly outperforms various state-of-the-art collaborative approaches whilst enhancing computational efficiency.
User-Inspired Posterior Network for Recommendation Reason Generation
A user-inspired multi-source posterior transformer (MSPT) is proposed, which induces the model reflecting the users' interests with a posterior multiple QA discussions module, and generating recommendation reasons containing the product attributes as well as the user-cared aspects.
Probing Product Description Generation via Posterior Distillation
An adaptive posterior network based on Transformer architecture that can utilize user-cared information from customer reviews is proposed that is superior to traditional generative models in both automatic indicators and human evaluation.
Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization
- Lei Shen, Haolan Zhan, X. Shen, Hongshen Chen, Xiaofang Zhao, Xiaodan Zhu
- Computer ScienceInternational Conference on Information and…
- 14 September 2021
This paper presents a data filtering method for open-domain dialogues, which identifies untrustworthy samples from training data with a quality measure that linearly combines seven dialogue attributes, and proposes a training framework that integrates maximum likelihood estimation (MLE) and negative training method (NEG).