Automatic Sense Prediction for Implicit Discourse Relations in Text

Loading...
Thumbnail Image
Penn collection
Departmental Papers (CIS)
Degree type
Discipline
Subject
Computer Sciences
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Pitler, Emily
Louis, Annie
Contributor
Abstract

We present a series of experiments on automatically identifying the sense of implicit discourse relations, i.e. relations that are not marked with a discourse connective such as “but” or “because”. We work with a corpus of implicit relations present in newspaper text and report results on a test set that is representative of the naturally occurring distribution of senses. We use several linguistically informed features, including polarity tags, Levin verb classes, length of verb phrases, modality, context, and lexical features. In addition, we revisit past approaches using lexical pairs from unannotated text as features, explain some of their shortcomings and propose modifications. Our best combination of features outperforms the baseline from data intensive approaches by 4% for comparison and 16% for contingency.

Advisor
Date of presentation
2009-08-01
Conference name
Departmental Papers (CIS)
Conference dates
2023-05-17T07:17:02.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Pitler, E., Louis, A., & Nenkova, A., Automatic Sense Prediction for Implicit Discourse Relations in Text, 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Aug. 2009, doi: http://www.aclweb.org/anthology/P09-1077
Recommended citation
Collection