paper-with-me

Papers

Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning

2022-10-01 · COLING 2022 10 · Zhichao Geng, Ming Zhong, Zhangyue Yin, Xipeng Qiu, Xuanjing Huang

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Dialogue SummarizationContrastive LearningText Summarization

Similar Papers 제목 키워드 기반

Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes

2020-09-15 · Xinyuan Zhang, Ruiyi Zhang, Manzil Zaheer, Amr Ahmed

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 Summarization

Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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 Summarization

Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization

2021-11-01 · EMNLP (newsum) 2021 11 · Dongyub Lee, Jungwoo Lim, Taesun Whang, Chanhee Lee 외

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 Summarization

Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization

2022-09-01 · Hyunjae Lee, Jaewoong Yun, Hyunjin Choi, Seongho Joe 외

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+5

Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts

2018-09-15 · Chih-Wen Goo, Yun-Nung Chen

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