UNIBA: distributional semantics for textual similarity

Authors:
Annalina Caputo;Pierpaolo Basile;Giovanni Semeraro
Affiliations:
University of Bari "Aldo Moro" Via E. Orabona, Bari, Italy;University of Bari "Aldo Moro" Via E. Orabona, Bari, Italy;University of Bari "Aldo Moro" Via E. Orabona, Bari, Italy
Venue:
SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
Year:
2012

Citing 4
Cited 0

Sparse Distributed Memory

Sparse Distributed Memory
A context-theoretic framework for compositionality in distributional semantics

Computational Linguistics
Encoding syntactic dependencies by vector permutation

GEMS '11 Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics
SemEval-2012 task 6: a pilot on semantic textual similarity

SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We report the results of UNIBA participation in the first SemEval-2012 Semantic Textual Similarity task. Our systems rely on distributional models of words automatically inferred from a large corpus. We exploit three different semantic word spaces: Random Indexing (RI), Latent Semantic Analysis (LSA) over RI, and vector permutations in RI. Runs based on these spaces consistently outperform the baseline on the proposed datasets.