paper-with-me

홈 › Papers

Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation

2026-03-28 · Amir Zeldes, Katherine Conhaim, Lauren Levine arxiv

Despite a long tradition of work on extractive summarization, which by nature aims to recover the most important propositions in a text, little work has been done on operationalizing graded proposition salience in naturally occurring data. In this paper, we adopt graded summarization-based salience as a metric from previous work on Salient Entity Extraction (SEE) and adapt it to quantify proposition salience. We define the annotation task, apply it to a small multi-genre dataset, evaluate agreement and carry out a preliminary study of the relationship between our metric and notions of discourse unit centrality in discourse parsing following Rhetorical Structure Theory (RST).

📄 PDF Abstract BibTeX arXiv:2603.27358

Code (0)

등록된 구현이 없습니다.

Tasks

Discourse Parsing

Similar Papers 제목 키워드 기반

Attention2Minority: A salient instance inference-based multiple instance learning for classifying small lesions in whole slide images

2023-01-18 · Ziyu Su, Mostafa Rezapour, Usama Sajjad, Metin Nafi Gurcan 외

Multiple instance learning (MIL) models have achieved remarkable success in analyzing whole slide images (WSIs) for disease classification problems. However, with regard to gigapixel WSI classification problems, current …

ClassificationMultiple Instance Learningwhole slide images

Abnormal Object Recognition: A Comprehensive Study

2014-11-09 · Babak Saleh, Ali Farhadi, Ahmed Elgammal

When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting. We argue that abnormalities and deviations from typicalities are among the most important components that …

Anomaly DetectionObjectObject Recognition

A study of parameters affecting visual saliency assessment

2013-07-22 · Nicolas Riche, Matthieu Duvinage, Matei Mancas, Bernard Gosselin 외

Since the early 2000s, computational visual saliency has been a very active research area. Each year, more and more new models are published in the main computer vision conferences. Nowadays, one of the big challenges is…

Proposition-Level Clustering for Multi-Document Summarization

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate informatio…

ClusteringDocument SummarizationMulti-Document SummarizationSentence+1

Proposition-Level Clustering for Multi-Document Summarization

2021-12-16 · NAACL 2022 7 · Ori Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru 외

Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate informatio…

ClusteringDocument SummarizationMulti-Document SummarizationSentence+1