EMNLP Findings2020
Pretrained Language Models for Dialogue Generation with Multiple Input Sources
Yu Cao, Wei Bi, Meng Fang, Dacheng Tao
摘要
Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks. However, it is still under investigating how to apply them to dialogue generation tasks, especially those with responses conditioned on multiple sources. Previous work simply concatenates all input sources or averages information from different input sources. In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2. We explore various methods to fuse multiple separate attention information corresponding to different sources. Our experimental results show that proper fusion methods deliver higher relevance with dialogue history than simple fusion baselines.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 4 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation 引用了 A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation
- SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation 引用了 A Pre-Training Based Personalized Dialogue Generation Model with Persona-Sparse Data
引用它的顶会 Paper4
- DialogLM: Pre-trained Model for Long Dialogue Understanding and SummarizationMing Zhong, Yang Liu, Yichong Xu, Chenguang Zhu 等AAAI 2022 · 150 次引用
- SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluationJunkai Zhou, Liang Pang, Huawei Shen, Xueqi ChengACL 2023 · 6 次引用
- TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language ModelsJie He, Bo Peng, Yi Liao, Qun Liu 等ACL 2021
- A Model-agnostic Data Manipulation Method for Persona-based Dialogue GenerationYu Cao, Wei Bi, Meng Fang, Shuming Shi 等ACL 2022
它引用的 Paper1
相关 Paper
- Multi-Stage Prompting for Knowledgeable Dialogue GenerationZihan Liu, Mostofa Patwary, Ryan Prenger, Shrimai Prabhumoye 等ACL Findings 2022 · 45 次引用
- Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao 等EMNLP 2020 · 153 次引用
- Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue GenerationXueliang Zhao, Yuxuan Wang, Chongyang Tao, Chenshuo Wang 等EMNLP Findings 2022 · 5 次引用
- Multi-Source Probing for Open-Domain Conversational UnderstandingYuanxi Li, Hao Zhou, Jie Zhou, Minlie HuangEMNLP 2023
- Generating Images with Multimodal Language ModelsJing Yu Koh, Daniel Fried, Russ SalakhutdinovNeurIPS 2023 · 403 次引用
