Lune

EMNLP Findings2022

Conversation Disentanglement with Bi-Level Contrastive Learning

Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao

Abstract

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance relations but pay inadequate attention to the utterance-to-context relation modeling. Second, a huge amount of human annotated data is required for training, which is expensive to obtain in practice. To address these issues, we propose a general disentangle model based on bi-level contrastive learning. It brings closer utterances in the same session while encourages each utterance to be near its clustered session prototypes in the representation space. Unlike existing approaches, our disentangle model works in both supervised settings with labeled data and unsupervised settings when no such data is available. The proposed method achieves new state-of-the-art performance results on both settings across several public datasets.

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.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Unsupervised Learning of Visual Features by Contrasting Cluster Assignments cites Data-Efficient Image Recognition with Contrastive Predictive Coding
  • Unsupervised Learning of Visual Features by Contrasting Cluster Assignments cites A Simple Framework for Contrastive Learning of Visual Representations
  • Unsupervised Learning of Visual Features by Contrasting Cluster Assignments cites Supervised Contrastive Learning
  • A Simple Framework for Contrastive Learning of Visual Representations cites Data-Efficient Image Recognition with Contrastive Predictive Coding
  • Supervised Contrastive Learning cites Data-Efficient Image Recognition with Contrastive Predictive Coding
  • Supervised Contrastive Learning cites A Simple Framework for Contrastive Learning of Visual Representations
  • SimCSE: Simple Contrastive Learning of Sentence Embeddings cites A Simple Framework for Contrastive Learning of Visual Representations
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene HallucinationHao Fei, Qian Liu, Meishan Zhang, Min Zhang et al.ACL 2023 · 45 citations

Builds on16

  1. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  2. Supervised Contrastive LearningPrannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna et al.NeurIPS 2020 · 7,049 citations
  3. Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsMathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal et al.NeurIPS 2020 · 5,249 citations
  4. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
  5. Data-Efficient Image Recognition with Contrastive Predictive CodingOlivier J. HénaffICML 2020 · 1,553 citations

Related papers

  1. Unsupervised Conversation Disentanglement through Co-TrainingHui Liu, Zhan Shi, Xiaodan ZhuEMNLP 2021 · 20 citations
  2. Disentangled Multiplex Graph Representation LearningYujie Mo, Yajie Lei, Jialie Shen, Xiaoshuang Shi et al.ICML 2023 · 35 citations
  3. Learning Disentangled Representation via Domain Adaptation for Dialogue SummarizationJinpeng Li, Yingce Xia, Xin Cheng, Dongyan Zhao et al.WWW 2023 · 12 citations
  4. Pre-training Multi-party Dialogue Models with Latent Discourse InferenceYiyang Li, Xinting Huang, Wei Bi, Hai ZhaoACL 2023 · 3 citations
  5. Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in ConversationsGeng Tu, Bin Liang, Ruibin Mao, Min Yang et al.ACL Findings 2023 · 24 citations
Dusk over the sea between two cliffs drawn in fine vertical lines