Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning
Pre-trained models have brought remarkable success on the text summarization task. For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed. As a result, existing summarization systems based on pre-trained models are unable to recognize the unique format of the speaker-utterance pair well in the dialogue. To investigate this issue, we conduct probing tests and manual analysis, and find that the powerful pre-trained model can not identify different speakers well in the conversation, which leads to various factual errors. Moreover, we propose three speaker-aware supervised contrastive learning (SCL) tasks: Token-level SCL, Turn-level SCL, and Global-level SCL. Comprehensive experiments demonstrate that our methods achieve significant performance improvement on two mainstream dialogue summarization datasets. According to detailed human evaluations, pre-trained models equipped with SCL tasks effectively generate summaries with better factual consistency.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstractive Dialogue SummarizationContrastive LearningText SummarizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes
High-quality dialogue-summary paired data is expensive to produce and domain-sensitive, making abstractive dialogue summarization a challenging task. In this work, we propose the first unsupervised abstractive dialogue s…
Abstractive Dialogue Summarizationdialogue summarySentenceText SummarizationImproving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning
Pre-trained models have brought remarkable success on the text summarization task. For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed. As a re…
Abstractive Dialogue SummarizationContrastive LearningText SummarizationCapturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization
In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it …
Abstractive Dialogue SummarizationEnhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization
Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natur…
Abstractive Dialogue SummarizationAbstractive Text SummarizationArticlesDecoder+5Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts
Neural abstractive summarization has been increasingly studied, where the prior work mainly focused on summarizing single-speaker documents (news, scientific publications, etc). In dialogues, there are different interact…
Abstractive Dialogue SummarizationAbstractive Text SummarizationSentence