Paper Info
Title
Probing The Linguistic Strengths And Limitations Of Unsupervised Grammar Induction
Abstract
Work in grammar induction should help shed light on the amount of syntactic structure that is discoverable from raw word or tag sequences. But since most current grammar induction algorithms produce unlabeled dependencies, it is difficult to analyze what types of constructions these algorithms can or cannot capture, and, therefore, to identify where additional supervision may be necessary. This paper provides an in-depth analysis of the errors made by unsupervised CCG parsers by evaluating them against the labeled dependencies in CCGbank, hinting at new research directions necessary for progress in grammar induction.
Year
Venue
Field
2015
PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1
Grammar induction,Computer science,Artificial intelligence,Natural language processing,Parsing,Syntactic structure
DocType
Volume
Citations 
Conference
P15-1
3
PageRank 
References 
Authors
0.39
12
2
Name
Order
Citations
PageRank
Yonatan Bisk119617.54
Julia Hockenmaier21782114.23