ABSTRACT
In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering.
- Bar Haim, R., Dagan, I., Dolan, B., Ferro, L., Giampiccolo, D., Magnini, B., & Szpektor, I. (2006). The II PASCAL RTE challenge. PASCAL Challenges Workshop. Venice, Italy.Google Scholar
- Bikel, D., Schwartz, R., & Weischedel, R. (1999). An Algorithm that Learns What's in a Name. Machine Learning, Special Issue on Natural Language Learning. Google ScholarDigital Library
- Boughorbel, S., Tarel, J.-P., & Fleuret, F. (2004). Non-mercer kernel for SVM object recognition. Proceedings of BMVC 2004. London, England.Google ScholarCross Ref
- Charniak, E. (2000). A maximum-entropy-inspired parser. Proc. of the 1st NAACL. Seattle, Washington, USA. Google ScholarDigital Library
- Collins, M., & Duffy, N. (2002). New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron. Proceedings of ACL02. Morristown, NJ, USA. Google ScholarDigital Library
- Corley, C., & Mihalcea, R. (2005). Measuring the semantic similarity of texts. Proc. of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment. Ann Arbor, Michigan, USA. Google ScholarDigital Library
- Cumby, C., & Roth, D. (2003). Kernel methods for relational learning. Proceedings of ICML 2003. Washington, DC, USA.Google Scholar
- Dagan, I., Glickman, O., & Magnini, B. (2005). The PASCAL RTE challenge. PASCAL Challenges Workshop. Southampton, U.K.Google Scholar
- Getoor, L. (2005). Tutorial on statistical relational learning. ILP (p. 415). Google ScholarDigital Library
- Haasdonk, B. (2005). Feature space interpretation of SVMs with indefinite kernels. IEEE Trans Pattern Anal Mach Intell, 27. Google ScholarDigital Library
- Joachims, T. (1999). Making large-scale svm learning practical. Advances in Kernel Methods-Support Vector Learning. MIT Press. Google ScholarDigital Library
- Miller, G. A. (1995). WordNet: A lexical database for English. Communications of the ACM. Google ScholarDigital Library
- Moschitti, A. (2006). Efficient convolution kernels for dependency and constituent syntactic trees. Proceedings of ECML, Berlin, Germany. Google ScholarDigital Library
- Peñnas, A., Rodrigo, A., Sama, V., & Verdejo, F. (2006). Overview of the answer validation exercise 2006. Working Notes for the CLEF 2006 Workshop. Alicante, Spain.Google Scholar
- Ponte, J. M., & Croft, W. B. (1998). A language modeling approach to information retrieval. Proceedings of SIGIR '98. New York, NY, USA. Google ScholarDigital Library
- Voorhees, E. M. (2003). Overview of TREC 2003. TREC.Google Scholar
- Zanzotto, F. M., & Moschitti, A. (2006). Automatic learning of textual entailments with cross-pair similarities. Proceedings of the 21st Coling and 44th ACL. Sydney, Australia. Google ScholarDigital Library
- Zelenko, D., Aone, C., & Richardella, A. (2003). Kernel methods for relation extraction. Journal of Machine Learning Research. Google ScholarDigital Library
- Fast and effective kernels for relational learning from texts
Recommendations
High-performance tagging on medical texts
COLING '04: Proceedings of the 20th international conference on Computational LinguisticsWe ran both Brill's rule-based tagger and TNT, a statistical tagger, with a default German newspaper-language model on a medical text corpus. Supplied with limited lexicon resources, TNT outperforms the Brill tagger with state-of-the-art performance ...
Deep Learning-Based Morphological Taggers and Lemmatizers for Annotating Historical Texts
DATeCH2019: Proceedings of the 3rd International Conference on Digital Access to Textual Cultural HeritagePart-of-speech tagging, morphological tagging, and lemmatization of historical texts pose special challenges due to the high spelling variability and the lack of large, high-quality training corpora. Researchers therefore often first map the words to ...
Word Sense Disambiguation with Specification Marks in Unrestricted Texts
DEXA '00: Proceedings of the 11th International Workshop on Database and Expert Systems ApplicationsThe authors present a method for the automatic disambiguating of nouns in English texts, using the notion of specification marks and employing the noun taxonomy of the WordNet lexical knowledge base (G.A. Miller et al., 1990). The method resolves the ...
Comments