The role of domain information in Word Sense Disambiguation
Natural Language Engineering
Direct word sense matching for lexical substitution
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Investigating lexical substitution scoring for subtitle generation
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Lexical reference: a semantic matching subtask
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Instance-based ontology population exploiting named-entity substitution
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
COLEUR and COLSLM: A WSD approach to multilingual lexical substitution, tasks 2 and 3 SemEval 2010
SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
An efficient indexer for large N-gram corpora
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Systems Demonstrations
Latent vector weighting for word meaning in context
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Acquiring thesauri from wikis by exploiting domain models and lexical substitution
ESWC'10 Proceedings of the 7th international conference on The Semantic Web: research and Applications - Volume Part II
Computational approaches to sentence completion
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
A challenge set for advancing language modeling
WLM '12 Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT
| Hi-index | 0.00 |
This paper summarizes FBK-irst participation at the lexical substitution task of the Semeval competition. We submitted two different systems, both exploiting synonym lists extracted from dictionaries. For each word to be substituted, the systems rank the associated synonym list according to a similarity metric based on Latent Semantic Analysis and to the occurrences in the Web 1T 5-gram corpus, respectively. In particular, the latter system achieves the state-of-the-art performance, largely surpassing the baseline proposed by the organizers.