This paper reports the description and perfor- mance of our system, FBK-HLT, participat- ing in the SemEval 2015, Task #2 “Semantic Textual Similarity”, English subtask. We sub- mitted three runs with different hypothesis in combining typical features (lexical similarity, string similarity, word n-grams, etc) with syn- tactic structure features, resulting in different sets of features. The results evaluated on both STS 2014 and 2015 datasets prove our hypoth- esis of building a STS system taking into con- sideration of syntactic information. We out- perform the best system on STS 2014 datasets and achieve a very competitive result to the best system on STS 2015 datasets.

FBK-HLT: A New Framework for Semantic Textual Similarity

Ngoc Phuoc An, Vo;Magnolini, Simone;Popescu, Octavian
2015

Abstract

This paper reports the description and perfor- mance of our system, FBK-HLT, participat- ing in the SemEval 2015, Task #2 “Semantic Textual Similarity”, English subtask. We sub- mitted three runs with different hypothesis in combining typical features (lexical similarity, string similarity, word n-grams, etc) with syn- tactic structure features, resulting in different sets of features. The results evaluated on both STS 2014 and 2015 datasets prove our hypoth- esis of building a STS system taking into con- sideration of syntactic information. We out- perform the best system on STS 2014 datasets and achieve a very competitive result to the best system on STS 2015 datasets.
978-1-941643-40-2
File in questo prodotto:
File Dimensione Formato  
FBK-HLT- A New Framework for Semantic Textual Similarity.pdf

accesso aperto

Licenza: Creative commons
Dimensione 301.76 kB
Formato Adobe PDF
301.76 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/302179
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact