Unsupervised Multi-Granularity Summarization
Text summarization is a user-preference based task. For one document, users often have different priorities for summary. Granularity level of the summary is a core component of these preferences. However, most existing studies focus solely on single-granularity scenarios, resulting in models that are limited to producing summaries with similar semantic coverage and are not customizable. In this paper, we propose the first unsupervised multi-granularity summarization framework, GranuSum. We regard events as basic semantic units of the original text and design a model that can take these events as anchors when generating summary. Meanwhile, by ranking these hint events and controlling the number of events, GranuSum is capable of generating summaries at different granularities in an unsupervised manner. We develop a testbed for the multi-granularity summarization task, including a new human-annotated benchmark GranuDUC where each document is paired with multiple summaries with different granularities. Extensive experiments on this benchmark and other large-scale datasets show that GranuSum substantially outperforms previous baselines. We also find that GranuSum exhibits impressive performance on conventional unsupervised abstractive summarization tasks via exploiting the event information, achieving new state-of-the-art results on three summarization datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstractive Text SummarizationText SummarizationSimilar Papers 제목 키워드 기반
Unsupervised Multi-Granularity Summarization
Text summarization is a user-preference based task, i.e., for one document, users often have different priorities for summary. As a key aspect of customization in summarization, granularity is used to measure the semanti…
Abstractive Text SummarizationText SummarizationScientific Paper Extractive Summarization Enhanced by Citation Graphs
In a citation graph, adjacent paper nodes share related scientific terms and topics. The graph thus conveys unique structure information of document-level relatedness that can be utilized in the paper summarization task,…
Extractive SummarizationLink PredictionSentenceAn Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks
Unsupervised summarization methods have achieved remarkable results by incorporating representations from pre-trained language models. However, existing methods fail to consider efficiency and effectiveness at the same t…
Document SummarizationMulti-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization
In this paper, we propose a multi-granularity interaction network for extractive and abstractive multi-document summarization, which jointly learn semantic representations for words, sentences, and documents. The word re…
Document SummarizationExtractive SummarizationMulti-Document SummarizationSentenceUnsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we …
Abstractive Text SummarizationOpinion SummarizationSentence