Trigger-Pair Predictors in Parsing and Tagging

In this article, we apply to natural language parsing and tagging the device of triggerpair predictors, previously employed exclusively within the field of language modelling for speech recognition. Given the task of predicting the correct rule to associate with a parse-tree node, or the correct tag to associate with a word of text, and assuming a particular class of parsing or tagging model, we quantify the information gain realized by taking account of rule or tag trigger-pair predictors, i.e. pairs consisting of a "triggering" rule or tag which has already occurred in the document being processed, together with a specific "triggered" rule or tag whose probability of occurrence within the current sentence we wish to estimate. This information gain is shown to be substantial. Further, by utilizing trigger pairs taken from the same general sort of document as is being processed (e.g. same subject matter or same discourse type)--as opposed to predictors derived from...

• Type: Conference
• Year: 1998
• Where: ACL
• Authors: Ezra Black, Andrew M. Finch, Hideki Kashioka
• Keywords: ACL 1998, ACL 2007, Information Gain, Natural Language Parsing, Tag Trigger-pair Predictors