Computer systems that learn: classification and prediction methods from statistics, neural nets, machine learning, and expert systems
Inferring the environment in a text-to-scene conversion system
Proceedings of the 1st international conference on Knowledge capture
Using the web to obtain frequencies for unseen bigrams
Computational Linguistics - Special issue on web as corpus
Extracting paraphrases from a parallel corpus
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Metonymy resolution as a classification task
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Using the web to overcome data sparseness
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Extracting structural paraphrases from aligned monolingual corpora
PARAPHRASE '03 Proceedings of the second international workshop on Paraphrasing - Volume 16
Acquisition of semantic classes for adjectives from distributional evidence
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Resolving paraphrases to support modeling language perception in an intelligent agent
STEP '08 Proceedings of the 2008 Conference on Semantics in Text Processing
Two types of Korean light verb constructions in a typed feature structure grammar
MWE '11 Proceedings of the Workshop on Multiword Expressions: from Parsing and Generation to the Real World
Hi-index | 0.00 |
In this paper we investigate polysemous adjectives whose meaning varies depending on the nouns they modify (e.g., fast). We acquire the meanings of these adjectives from a large corpus and propose a probabilistic model which provides a ranking on the set of possible interpretations. We identify lexical semantic information automatically by exploiting the consistent correspondences between surface syntactic cues and lexical meaning. We evaluate our results against paraphrase judgments elicited experimentally from humans and show that the model's ranking of meanings correlates reliably with human intuitions: meanings that are found highly probable by the model are also rated as plausible by the subjects.