Understanding Points of Correspondence between Sentences for Abstractive Summarization

• URL: http://arxiv.org/abs/2006.05621v1
• Date: Wed, 10 Jun 2020 02:42:38 GMT
• Title: Understanding Points of Correspondence between Sentences for Abstractive Summarization
• Authors: Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim, Lidan Wang, Walter Chang, Fei Liu
• Abstract summary: We present an investigation into fusing sentences drawn from a document by introducing the notion of points of correspondence. We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences.
• Score: 39.7404761923196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fusing sentences containing disparate content is a remarkable human ability that helps create informative and succinct summaries. Such a simple task for humans has remained challenging for modern abstractive summarizers, substantially restricting their applicability in real-world scenarios. In this paper, we present an investigation into fusing sentences drawn from a document by introducing the notion of points of correspondence, which are cohesive devices that tie any two sentences together into a coherent text. The types of points of correspondence are delineated by text cohesion theory, covering pronominal and nominal referencing, repetition and beyond. We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences. Our dataset bridges the gap between coreference resolution and summarization. It is publicly shared to serve as a basis for future work to measure the success of sentence fusion systems. (https://github.com/ucfnlp/points-of-correspondence)

Related papers

• Thesis: Document Summarization with applications to Keyword extraction and Image Retrieval [0.0]
  We propose a set of submodular functions for opinion summarization. Opinion summarization has built in it the tasks of summarization and sentiment detection. Our functions generate summaries such as there is good correlation between document sentiment and summary sentiment along with good ROUGE score.
  arXiv  Detail & Related papers  (2024-05-20T21:27:18Z)
• `Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory [22.659031563705245]
  In this paper, we aim to enforce cohesion whilst controlling for informativeness and redundancy in summaries. Our sentence selector simulates human memory to keep track of topics. It is possible to extract highly cohesive summaries that nevertheless read as informative to humans.
  arXiv  Detail & Related papers  (2024-02-16T12:43:26Z)
• RankSum An unsupervised extractive text summarization based on rank fusion [0.0]
  We propose Ranksum, an approach for extractive text summarization of single documents. The Ranksum obtains the sentence saliency rankings corresponding to each feature in an unsupervised way. We evaluate our approach on publicly available summarization datasets CNN/DailyMail and DUC 2002.
  arXiv  Detail & Related papers  (2024-02-07T22:24:09Z)
• Aspect-based Meeting Transcript Summarization: A Two-Stage Approach with Weak Supervision on Sentence Classification [91.13086984529706]
  Aspect-based meeting transcript summarization aims to produce multiple summaries. Traditional summarization methods produce one summary mixing information of all aspects. We propose a two-stage method for aspect-based meeting transcript summarization.
  arXiv  Detail & Related papers  (2023-11-07T19:06:31Z)
• PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition [63.51569687229681]
  We argue for the need to recognize the textual entailment relation of each proposition in a sentence individually. We propose PropSegmEnt, a corpus of over 45K propositions annotated by expert human raters. Our dataset structure resembles the tasks of (1) segmenting sentences within a document to the set of propositions, and (2) classifying the entailment relation of each proposition with respect to a different yet topically-aligned document.
  arXiv  Detail & Related papers  (2022-12-21T04:03:33Z)
• Relational Sentence Embedding for Flexible Semantic Matching [86.21393054423355]
  We present Sentence Embedding (RSE), a new paradigm to discover further the potential of sentence embeddings. RSE is effective and flexible in modeling sentence relations and outperforms a series of state-of-the-art embedding methods.
  arXiv  Detail & Related papers  (2022-12-17T05:25:17Z)
• Consistency and Coherence from Points of Contextual Similarity [0.0]
  ESTIME measure, recently proposed specifically for factual consistency, achieves high correlations with human expert scores. This is not a problem for current styles of summarization, but it may become an obstacle for future summarization systems.
  arXiv  Detail & Related papers  (2021-12-22T03:04:20Z)
• Reinforcing Semantic-Symmetry for Document Summarization [15.113768658584979]
  Document summarization condenses a long document into a short version with salient information and accurate semantic descriptions. This paper introduces a new textbfreinforcing stextbfemantic-textbfsymmetry learning textbfmodel is proposed for document summarization. A series of experiments have been conducted on two wildly used benchmark datasets CNN/Daily Mail and BigPatent.
  arXiv  Detail & Related papers  (2021-12-14T17:41:37Z)
• Paragraph-level Commonsense Transformers with Recurrent Memory [77.4133779538797]
  We train a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives. Our results show that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.
  arXiv  Detail & Related papers  (2020-10-04T05:24:12Z)
• Extractive Summarization as Text Matching [123.09816729675838]
  This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. We formulate the extractive summarization task as a semantic text matching problem. We have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1)
  arXiv  Detail & Related papers  (2020-04-19T08:27:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.