EMNLP Findings2023
Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue
Tingchen Fu, Xueliang Zhao, Lemao Liu, Rui Yan
Abstract
Multi-turn response selection aims to retrieve a response for a dialogue context from a candidate pool and negative sampling is the key to its retrieval performance. However, previous methods of negative samples tend to yield false negatives due to the one-to-many property in open-domain dialogue, which is detrimental to the optimization process. To deal with the problem, we propose a sequential variational ladder auto-encoder to capture the diverse oneto-many transition pattern of multiple characteristics in open-domain dialogue. The learned transition logic thus assists in identifying potential positives in disguise. Meanwhile, we propose a TRIGGER framework to adjust negative sampling in the training process such that the scope of false negatives dynamically updates according to the model capacity. Extensive experiments on two benchmarks verify the effectiveness of our approach.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on15
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang et al.ICLR 2021 · 1,547 citations
- Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based DialoguesRuijian Xu, Chongyang Tao, Daxin Jiang, Xueliang Zhao et al.AAAI 2021 · 76 citations
- Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionTaesun Whang, Dongyub Lee, Dongsuk Oh, Chanhee Lee et al.AAAI 2021 · 70 citations
- Multi-Facet Clustering Variational AutoencodersFabian Falck, Haoting Zhang, Matthew Willetts, George Nicholson et al.NeurIPS 2021 · 57 citations
- The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response SelectionZibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu et al.EMNLP 2020 · 32 citations
Related papers
- Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual InformationKun Zhao, Bohao Yang, Chenghua Lin, Wenge Rong et al.ACL 2023 · 14 citations
- Speculative Sampling in Variational Autoencoders for Dialogue Response GenerationShoetsu Sato, Naoki Yoshinaga, Masashi Toyoda, Masaru KitsuregawaEMNLP Findings 2021
- DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response GenerationWei Chen, Yeyun Gong, Song Wang, Bolun Yao et al.ACL 2022
- Negative Training for Neural Dialogue Response GenerationTianxing He, James R. GlassACL 2020 · 52 citations
- Generating Dialogue Responses from a Semantic Latent SpaceWei-Jen Ko, Avik Ray, Yilin Shen, Hongxia JinEMNLP 2020 · 4 citations
