The nature of statistical learning theory
The nature of statistical learning theory
Combining labeled and unlabeled data with co-training
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
A multilingual paradigm for automatic verb classification
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Word translation disambiguation using Bilingual Bootstrapping
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Out-of-context noun phrase semantic interpretation with cross-linguistic evidence
CIKM '06 Proceedings of the 15th ACM international conference on Information and knowledge management
Yago: a core of semantic knowledge
Proceedings of the 16th international conference on World Wide Web
Autonomously semantifying wikipedia
Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
Decoding wikipedia categories for knowledge acquisition
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
SemEval-2007 task 04: classification of semantic relations between nominals
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
A bilingual dictionary extracted from the Wikipedia link structure
DASFAA'08 Proceedings of the 13th international conference on Database systems for advanced applications
NLDB'05 Proceedings of the 10th international conference on Natural Language Processing and Information Systems
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Hi-index | 0.00 |
This paper proposes a novel framework called bilingual co-training for a large-scale, accurate acquisition method for monolingual semantic knowledge. In this framework, we combine the independent processes of monolingual semantic-knowledge acquisition for two languages using bilingual resources to boost performance. We apply this framework to large-scale hyponymy-relation acquisition from Wikipedia. Experimental results show that our approach improved the F-measure by 3.6--10.3%. We also show that bilingual co-training enables us to build classifiers for two languages in tandem with the same combined amount of data as required for training a single classifier in isolation while achieving superior performance.