Deterministic Choices in a Data-driven Parser

Jaf, Sardar; Ramsay, Allan; Sharp, Bernadette; Lubaszewski, Wieslaw; Delmonte, Rodolfo

Abstract

Data-driven parsers rely on recommendations from parse models, which are generated from a set of training data using a machine learning classifier, to perform parse operations. However, in some cases a parse model cannot recommend a parse action to a parser unless it learns from the training data what parse action(s) to take in every possible situation. Therefore, it will be hard for a parser to make an informed decision as to what parse operation to perform when a parse model recommends no/several parse actions to a parser. Here we examine the effect of various deterministic choices on a datadriven parser when it is presented with no/several recommendation from a parse model.

Citation

Jaf, S., Ramsay, A., Sharp, B., Lubaszewski, W., & Delmonte, R. (2015, September). Deterministic Choices in a Data-driven Parser. Presented at The 12th International Workshop on Natural Language Processing and Cognitive Science., Krakow, Poland

• Presentation Conference Type: Conference Paper (published)
• Conference Name: The 12th International Workshop on Natural Language Processing and Cognitive Science.
• Start Date: Sep 22, 2015
• End Date: Sep 24, 2015
• Acceptance Date: Sep 22, 2015
• Publication Date: Sep 22, 2015
• Deposit Date: Feb 12, 2016
• Publicly Available Date: Nov 14, 2016
• Pages: 95-103
• Book Title: Natural language processing and cognitive science : proceedings 2015.
• Public URL: https://durham-repository.worktribe.com/output/1152371
• Publisher URL: http://nlpcs2015.epi.uj.edu.pl/