An Algorithm that Learns What‘s in a Name
Machine Learning - Special issue on natural language learning
Automatic labeling of semantic roles
Computational Linguistics
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Integrating multiple knowledge sources to disambiguate word sense: an exemplar-based approach
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
The Proposition Bank: An Annotated Corpus of Semantic Roles
Computational Linguistics
Word Sense Disambiguation: Algorithms and Applications (Text, Speech and Language Technology)
Word Sense Disambiguation: Algorithms and Applications (Text, Speech and Language Technology)
Shallow Semantic Parsing Based on FrameNet, VerbNet and PropBank
Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
NAACL-Short '06 Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers
Introduction to the CoNLL-2005 shared task: semantic role labeling
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
What's in a preposition?: dimensions of sense disambiguation for an interesting word class
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Incorporating coercive constructions into a verb lexicon
RELMS '11 Proceedings of the ACL 2011 Workshop on Relational Models of Semantics
| Hi-index | 0.00 |
In Construction Grammar, structurally patterned units called constructions are assigned meaning in the same way that words are -- via convention rather than composition. That is, rather than piecing semantics together from individual lexical items, Construction Grammar proposes that semantics can be assigned at the construction level. In this paper, we investigate whether a classifier can be taught to identify these constructions and consider the hypothesis that identifying construction types can improve the semantic interpretation of previously unseen predicate uses. Our results show that not only can the constructions be automatically identified with high accuracy, but the classifier also performs just as well with out-of-vocabulary predicates.