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

Autor/in	Boxwell, Stephen A.
Titel	A CCG-Based Method for Training a Semantic Role Labeler in the Absence of Explicit Syntactic Training Data
Quelle	(2011), (146 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, The Ohio State University
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	978-1-2671-4081-4
Schlagwörter	Hochschulschrift; Dissertation; Natural Language Processing; Training; Programming; Computer System Design; Information Technology; Computer Software; Data; Computational Linguistics; Markov Processes + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Natürliche Sprache; Ausbildung; Programmierung; Informationstechnologie; Daten; Linguistics; Computerlinguistik; Markowscher Prozess
Abstract	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. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2017/4/10