RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy

Abstract

In the field of dialogue summarization, due to the lack of training data, it is often difficult for supervised summary generation methods to learn vital information from dialogue context. Several works on unsupervised summarization for document by leveraging semantic information solely or auto-encoder strategy (i.e., sentence compression), they however cannot be adapted to the dialogue scene due to the limited words in utterances and huge gap between the dialogue and its summary. In this study, we propose a novel unsupervised strategy to address this challenge, which roots from the hypothetical foundation that a superior summary approximates a replacement of the original dialogue, and they are roughly equivalent for auxiliary (self-supervised) tasks, e.g., dialogue generation. The proposed strategy Rep-Sum is applied to generate both extractive and abstractive summary with the guidance of the followed n th utterance generation and classification tasks. Extensive experiments on various datasets demonstrate the superiority of the proposed model compared with other unsupervised methods.

Improving Abstractive Dialogue Summarization Using Keyword Extraction

“…Moreover, owing to the lack of training data in dialogue summarization, learning vital information from the dialogue context becomes challenging. Fu et al [14] discussed the limited number of words in extractive summarization and the slight difference between the input and target summaries owing to the limitations of the unsupervised methodology [15]. Unlike the unsupervised approach that makes qualitative evaluation difficult, the supervised approach can be easily evaluated [16] even if there is no sufficient database for dialogue summarization.…”

Unsupervised Abstractive Dialogue Summarization with Word Graphs and POV Conversion

“…For meeting summaries, we compare our method with previous research on unsupervised dialogue summarization. Along with Filippova (2010), Shang et al (2018), andFu et al (2021), we select Boudin and Morin (2013) and Mehdad et al (2013) Table 3: Results on day-to-day, interview, screenplay, and debate summarization datasets. All reported scores are F-1 measures.…”

“…However, applying our POV module to already abstractive summarization systems resulted in higher scores in all cases. We attribute this to the fact that previous abstractive summarization systems do not generate sufficiently reportive summaries; past research either emphasize other linguistic aspects like hyponym conversion (Shang et al, 2018), or treat POV conversion as a byproduct of an end-to-end summarization pipeline (Fu et al, 2021).…”