Papers › Learning Dialogue Representations from Consecutive Utterances

Learning Dialogue Representations from Consecutive Utterances

26 May 2022NAACL 2022 7arXiv:2205.13568archive 2025-07-28

Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue tasks. DSE learns from dialogues by taking consecutive utterances of the same dialogue as positive pairs for contrastive learning. Despite its simplicity, DSE achieves significantly better representation capability than other dialogue representation and universal sentence representation models. We evaluate DSE on five downstream dialogue tasks that examine dialogue representation at different semantic granularities. Experiments in few-shot and zero-shot settings show that DSE outperforms baselines by a large margin. For example, it achieves 13% average performance improvement over the strongest unsupervised baseline in 1-shot intent classification on 6 datasets. We also provide analyses on the benefits and limitations of our model.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

amazon-research/dse officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive Learning Conversational Question Answering Conversational Response Selection Dialogue Act Classification Dialogue Management Dialogue Understanding Few-Shot Learning Goal-Oriented Dialogue Systems Intent Classification Intent Detection Out-of-Distribution Detection Question Answering Representation Learning Sentence Sentence Embedding Sentence-Embedding Task-Oriented Dialogue Systems intent-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BERT Contrastive Learning Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections