Output details
11 - Computer Science and Informatics
University of Edinburgh
Output title
Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification
Type
E - Conference contribution
DOI
-
Name of conference/published proceedings
Proceedings of the Conference on Empirical Methods in Natural Language Processing
Volume number
-
Issue number
-
First page of article
1223
ISSN of proceedings
-
Year of publication
2010
Number of additional authors
3
Additional information
<22> Originality: The computational advantages of Steedman's CCG grammar formalism are exploited in this work and related papers by the same authors (2011, 2012) to support a state of the art algorithm for semantic parser induction from paired sentences and logical forms such as database queries.
Significance: This is the most robust, general and non-language-specific program of its kind and results are state of the art across a wider range of languages.
Rigour: The program uses advanced wide-coverage robust statistical parsing modelling techniques, and has been rigorously evaluated against the competition using a number of standard datasets.
Interdisciplinary
-
Cross-referral requested
-
Research group
D - Institute for Language, Cognition & Computation
Citation count
9
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
