Probabilistic latent semantic indexing
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Distributional clustering of English words
ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
An unsupervised learning method for associative relationships between verb phrases
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Evaluating smoothing algorithms against plausibility judgements
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Learning surface text patterns for a Question Answering system
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Using the web to overcome data sparseness
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Japanese dependency analysis using cascaded chunking
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Text simplification for reading assistance: a project note
PARAPHRASE '03 Proceedings of the second international workshop on Paraphrasing - Volume 16
Zero-anaphora resolution by learning rich syntactic pattern features
ACM Transactions on Asian Language Information Processing (TALIP)
Exploiting lexical conceptual structure for paraphrase generation
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
| Hi-index | 0.00 |
This paper addresses the issue of post-transfer process in paraphrasing. Our previous investigation into transfer errors revealed that case assignment tends to be incorrect, irrespective of the types of transfer in lexical and structural paraphrasing of Japanese sentences [3]. Motivated by this observation, we propose an empirical method to detect incorrect case assignments. Our error detection model combines two error detection models that are separately trained on a large collection of positive examples and a small collection of manually labeled negative examples. Experimental results show that our combined model significantly enhances the baseline model which is trained only on positive examples. We also propose a selective sampling scheme to reduce the cost of collecting negative examples, and confirm the effectiveness in the error detection task.