Paper: RTM-DCU: Referential Translation Machines for Semantic Similarity

ACL ID S14-2085
Title RTM-DCU: Referential Translation Machines for Semantic Similarity
Venue Joint Conference on Lexical and Computational Semantics
Session
Year 2014
Authors

We use referential translation machines (RTMs) for predicting the semantic simi- larity of text. RTMs are a computational model for identifying the translation acts between any two data sets with respect to interpretants selected in the same do- main, which are effective when making monolingual and bilingual similarity judg- ments. RTMs judge the quality or the se- mantic similarity of text by using retrieved relevant training data as interpretants for reaching shared semantics. We derive fea- tures measuring the closeness of the test sentences to the training data via inter- pretants, the difficulty of translating them, and the presence of the acts of transla- tion, which may ubiquitously be observed in communication. RTMs provide a lan- guage independent approach to all simi- larity task...