# Conversation Disentanglement with Bi-Level Contrastive Learning

arXiv: https://arxiv.org/abs/2210.15265 · HTML: https://mlsanity.com/paper/2210.15265/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Unsupervised Embedding Learning via Invariant and Spreading Instance Feature](https://mlsanity.com/paper/1904.03436/) (2019)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Response Selection for Multi-Party Conversations with Dynamic Topic Tracking](https://mlsanity.com/paper/2010.07785/) (2020)
- [Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer](https://mlsanity.com/paper/1911.10666/) (2019)
- [Online Conversation Disentanglement with Pointer Networks](https://mlsanity.com/paper/2010.11080/) (2020)
- [Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph](https://mlsanity.com/paper/2210.03037/) (2022)
- [DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement](https://mlsanity.com/paper/2004.03760/) (2020)
- [Unsupervised Conversation Disentanglement through Co-Training](https://mlsanity.com/paper/2109.03199/) (2021)
- [Structural Characterization for Dialogue Disentanglement](https://mlsanity.com/paper/2110.08018/) (2021)
- [Findings on Conversation Disentanglement](https://mlsanity.com/paper/2112.05346/) (2021)
- [Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2004.01940/) (2020)
- [Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection](https://mlsanity.com/paper/2110.12646/) (2021)

## Built on by (most cited first, 6 of 6)

- [Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination](https://mlsanity.com/paper/2305.12256/) (2023)
- [Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment](https://mlsanity.com/paper/2305.12260/) (2023)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [Dramatic Conversation Disentanglement](https://mlsanity.com/paper/2305.16648/) (2023)
- [Revisiting Conversation Discourse for Dialogue Disentanglement](https://mlsanity.com/paper/2306.03975/) (2023)
- [A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition](https://mlsanity.com/paper/2308.04424/) (2023)

## Abstract (arXiv)

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, 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 setting with labeled data and unsupervised setting when no such data is available. The proposed method achieves new state-of-the-art performance on both settings across several public datasets.