This paper presents the UNITOR system that participated in the ∗SEM 2013 shared task on Semantic Textual Similarity (STS). The task is modeled as a Support Vector (SV) regression problem, where a similarity scoring function between text pairs is acquired from examples. The proposed approach has been implemented in a system that aims at providing high applicability and robustness, in order to reduce the risk of over-fitting over a specific datasets. Moreover, the approach does not require any manually coded resource (e.g. WordNet), but mainly exploits distributional analysis of unlabeled corpora. A good level of accuracy is achieved over the shared task: in the Typed STS task the proposed system ranks in 1st and 2nd position.
Croce, D., Storch, V., Basili, R. (2013). UNITOR-CORE TYPED: Combining Text Similarity and Semantic Filters through SV Regression. In Second joint conference on lexical and computational semantics (*SEM), Volume 1: proceedings of the main conference and the shared task: semantic textual similarity (pp.59-65). Association for Computational Linguistics (ACL).
UNITOR-CORE TYPED: Combining Text Similarity and Semantic Filters through SV Regression
Croce D.;Basili R.
2013-01-01
Abstract
This paper presents the UNITOR system that participated in the ∗SEM 2013 shared task on Semantic Textual Similarity (STS). The task is modeled as a Support Vector (SV) regression problem, where a similarity scoring function between text pairs is acquired from examples. The proposed approach has been implemented in a system that aims at providing high applicability and robustness, in order to reduce the risk of over-fitting over a specific datasets. Moreover, the approach does not require any manually coded resource (e.g. WordNet), but mainly exploits distributional analysis of unlabeled corpora. A good level of accuracy is achieved over the shared task: in the Typed STS task the proposed system ranks in 1st and 2nd position.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.