Paper Info
Title
Inductive detection of language features via clustering minimal pairs: toward feature-rich grammars in machine translation
Abstract
Syntax-based Machine Translation systems have recently become a focus of research with much hope that they will outperform traditional Phrase-Based Statistical Machine Translation (PBSMT). Toward this goal, we present a method for analyzing the morphosyntactic content of language from an Elicitation Corpus such as the one included in the LDC's upcoming LCTL language packs. The presented method discovers a mapping between morphemes and linguistically relevant features. By providing this tool that can augment structure-based MT models with these rich features, we believe the discriminative power of current models can be improved. We conclude by outlining how the resulting output can then be used in inducing a morphosyntactically feature-rich grammar for AVENUE, a modern syntax-based MT system.
Year
Venue
Keywords
2008
SSST@ACL
morphosyntactic content,morphosyntactically feature-rich grammar,modern syntax-based mt system,syntax-based machine translation system,traditional phrase-based statistical machine,upcoming lctl language pack,inductive detection,discriminative power,current model,minimal pair,language feature,machine translation,mt model,linguistically relevant feature
Field
DocType
Citations 
Rule-based machine translation,Example-based machine translation,Computer science,Machine translation,Synchronous context-free grammar,Machine translation software usability,Artificial intelligence,Natural language processing,Computer-assisted translation,Syntax,Speech recognition,Transfer-based machine translation,Machine learning
Conference
0
PageRank 
References 
Authors
0.34
11
3
Name
Order
Citations
PageRank
Jonathan H. Clark141116.42
Robert Frederking2175.68
Lori S. Levin337246.46