Propositional Term Extraction over Short Text using Word Cohesiveness and Conditional Random Fields with Multi-Level Features

Ru Yng Chang, Chung Hsien Wu

Research output: Contribution to conferencePaperpeer-review

Abstract

Propositional terms in a research abstract (RA) generally convey the most important information for readers to quickly glean the contribution of a research article. This paper considers propositional term extraction from RAs as a sequence labeling task using the IOB (Inside, Outside, Beginning) encoding scheme. In this study, conditional random fields (CRFs) are used to initially detect the propositional terms, and the combined association measure (CAM) is applied to further adjust the term boundaries. This method can extract beyond simply NP-based propositional terms by combining multi-level features and inner lexical cohesion. Experimental results show that CRFs can significantly increase the recall rate of imperfect boundary term extraction and the CAM can further effectively improve the term boundaries.

Original languageEnglish
Publication statusPublished - 2008
Event20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008 - Taipei, Taiwan
Duration: 2008 Sep 42008 Sep 5

Other

Other20th Conference on Computational Linguistics and Speech Processing, ROCLING 2008
Country/TerritoryTaiwan
CityTaipei
Period08-09-0408-09-05

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Speech and Hearing

Fingerprint

Dive into the research topics of 'Propositional Term Extraction over Short Text using Word Cohesiveness and Conditional Random Fields with Multi-Level Features'. Together they form a unique fingerprint.

Cite this