SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for multi-document summarization, in which we convert the original documents to a sentence graph, taking both linguistic and deep representation into account, then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary. Experiments on Multi-News and DUC-2004 datasets show that our method is competitive to previous unsupervised methods and is even comparable to the neural supervised approaches. In addition, human evaluation shows our system produces consistent and complete summaries compared to human written ones.
Code (1)
Tasks
ClusteringDocument SummarizationMulti-Document SummarizationSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline
The Scholarly Document Processing (SDP) workshop is to encourage more efforts on natural language understanding of scientific task. It contains three shared tasks and we participate in the LongSumm shared task. In this p…
ClusteringGraph Clusteringgraph constructionLanguage Modeling+5Monash-Summ@LongSumm 20 SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline
The Scholarly Document Processing (SDP) workshop is to encourage more efforts on natural language understanding of scientific task. It contains three shared tasks and we participate in the LongSumm shared task. In this p…
Graph Clusteringgraph constructionLanguage ModelingLanguage Modelling+4GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summa…
Document SummarizationInformativenessMulti-Document SummarizationSentenceAbstractive Unsupervised Multi-Document Summarization using Paraphrastic Sentence Fusion
In this work, we aim at developing an unsupervised abstractive summarization system in the multi-document setting. We design a paraphrastic sentence fusion model which jointly performs sentence fusion and paraphrasing us…
Abstractive Text SummarizationDocument SummarizationMachine TranslationMulti-Document Summarization+5Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge …
Document SummarizationExtractive Document SummarizationExtractive SummarizationExtractive Text Summarization+2