Skip to Main Content
 

Global Search Box

 
 
 
 

ETD Abstract Container

Abstract Header

A CCG-Based Method for Training a Semantic Role Labeler in the Absence of Explicit Syntactic Training Data

Boxwell, Stephen Arthur

Abstract Details

2011, Doctor of Philosophy, Ohio State University, Linguistics.
Treebanks are a necessary prerequisite for many NLP tasks, including, but not limited to, semantic role labeling. For many languages, however, treebanks are either nonexistent or too small to be useful. Time-critical applications may require rapid deployment of natural language software for a new critical language – much faster than the development time of a traditional treebank. This dissertation describes a method for generating a treebank and training syntactic and semantic models using only semantic training information – that is, no human-annotated syntactic training data whatsoever. This will greatly increase the speed of development of natural language tools for new critical languages in exchange for a modest drop in overall accuracy. Using Combinatory Categorial Grammar (CCG) in concert with Propbank semantic role annotations allows us to accurately predict lexical categories in combination with a partially hidden Markov model. By training the Berkeley parser on our generated syntactic data, we can achieve SRL performance of 65.5% without using a treebank, as opposed to 74% using the same feature set with gold-standard data.
Michael White (Advisor)
Chris Brew (Advisor)
William Schuler (Committee Member)
Simon Dennis (Committee Member)

Recommended Citations

Citations

  • Boxwell, S. A. (2011). A CCG-Based Method for Training a Semantic Role Labeler in the Absence of Explicit Syntactic Training Data [Doctoral dissertation, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1322594816

    APA Style (7th edition)

  • Boxwell, Stephen. A CCG-Based Method for Training a Semantic Role Labeler in the Absence of Explicit Syntactic Training Data. 2011. Ohio State University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1322594816.

    MLA Style (8th edition)

  • Boxwell, Stephen. "A CCG-Based Method for Training a Semantic Role Labeler in the Absence of Explicit Syntactic Training Data." Doctoral dissertation, Ohio State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=osu1322594816

    Chicago Manual of Style (17th edition)