Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization

2017-09-01 · WS 2017 9 · Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis

We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research. The framework allows summaries to be generated in a greedy way while preserving near-optimal performance guarantees. Our main contribution is the novel coverage reward term of the objective function optimized by the greedy algorithm. This component builds on the graph-of-words representation of text and the k-core decomposition algorithm to assign meaningful scores to words. We evaluate our approach on the AMI and ICSI meeting speech corpora, and on the DUC2001 news corpus. We reach state-of-the-art performance on all datasets. Results indicate that our method is particularly well-suited to the meeting domain.

📄 PDF Abstract BibTeX

Code (1)

Tixierae/EMNLP2017_NewSum 공식 구현

Tasks

Document SummarizationExtractive SummarizationExtractive Text Summarization Information Retrieval Keyword Extraction Sentence Compression Text Summarization Unsupervised Extractive Summarization

Combining Word Embeddings and N-grams for Unsupervised Document Summarization

2020-04-25 · Zhuolin Jiang, Manaj Srivastava, Sanjay Krishna, David Akodes 외

Graph-based extractive document summarization relies on the quality of the sentence similarity graph. Bag-of-words or tf-idf based sentence similarity uses exact word matching, but fails to measure the semantic similarit…

Diversity Document Summarization Extractive Document Summarization Extractive Summarization+8

Submodularity In Machine Learning and Artificial Intelligence

2022-01-31 · Jeff Bilmes

In this manuscript, we offer a gentle review of submodularity and supermodularity and their properties. We offer a plethora of submodular definitions; a full description of a number of example submodular functions and th…

Abstractive Text Summarization BIG-bench Machine Learning feature selection

Unsupervised Extractive Summarization with Heterogeneous Graph Embeddings for Chinese Document

2022-11-09 · Chen Lin, Ye Liu, Siyu An, Di Yin

In the scenario of unsupervised extractive summarization, learning high-quality sentence representations is essential to select salient sentences from the input document. Previous studies focus more on employing statisti…

Extractive Summarization Sentence Sentence Embeddings Unsupervised Extractive Summarization

Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers

2020-10-16 · Findings of the Association for Computational Linguistics 2020 · Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei 외

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 Summarization Extractive Document Summarization Extractive Summarization Extractive Text Summarization+2

Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders

2023-10-29 · Qianren Mao, Shaobo Zhao, Jiarui Li, Xiaolei Gu 외

Pre-trained sentence representations are crucial for identifying significant sentences in unsupervised document extractive summarization. However, the traditional two-step paradigm of pre-training and sentence-ranking, c…