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.
UNIBA: Distributional Semantics for Textual Similarity
CAPUTO, ANNALINA;BASILE, PIERPAOLO;SEMERARO, Giovanni
2012-01-01
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.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.