Paper Info
Title
A statistics-based semantic textual entailment system
Abstract
We present a Textual Entailment (TE) recognition system that uses semantic features based on the Universal Networking Language (UNL). The proposed TE system compares the UNL relations in both the text and the hypothesis to arrive at the two-way entailment decision. The system has been separately trained on each development corpus released as part of the Recognizing Textual Entailment (RTE) competitions RTE-1, RTE-2, RTE-3 and RTE-5 and tested on the respective RTE test sets.
Year
DOI
Venue
2011
10.1007/978-3-642-25324-9_23
MICAI
Keywords
Field
DocType
respective rte test set,recognizing textual entailment,universal networking language,statistics-based semantic textual entailment,competitions rte-1,development corpus,recognition system,unl relation,textual entailment,semantic feature,proposed te system
Logical consequence,Textual entailment,Recognition system,Computer science,Natural language processing,Universal Networking Language,Artificial intelligence
Conference
Volume
ISSN
Citations 
7094
0302-9743
4
PageRank 
References 
Authors
0.59
15
4
Name
Order
Citations
PageRank
Partha Pakray114733.24
Utsab Barman2593.72
Sivaji Bandyopadhyay3929107.30
Alexander Gelbukh42843269.19