Learning Dialogue Representations from Consecutive Utterances
This work addresses data scarcity in dialogue systems by providing a method for learning effective dialogue representations, though it is incremental as it builds on existing contrastive learning techniques.
The paper tackles the problem of learning high-quality dialogue representations for data-scarce dialogue systems by introducing Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method that uses consecutive utterances as positive pairs, resulting in a 13% average performance improvement over the strongest unsupervised baseline in 1-shot intent classification on 6 datasets.
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.