RTM-DCU: Referential Translation Machines for Semantic Similarity

We use referential translation machines (RTMs) for predicting the semantic similarity 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 domain, which are effective when making monolingual and bilingual similarity judgments. RTMs judge the quality or the semantic similarity of text by using retrieved relevant training data as interpretants for reaching shared semantics. We derive features measuring the closeness of the test sentences to the training data via interpretants, the difficulty of translating them, and the presence of the acts of translation, which may ubiquitously be observed in communication. RTMs provide a language independent approach to all similarity tasks and achieve top performance when predicting monolingual cross-level semantic similarity (Task 3) and good results in semantic relatedness and entailment (Task 1) and multilingual semantic textual similarity (STS) (Task 10). RTMs remove the need to access any task or domain specific information or resource. 1 Semantic Similarity Judgments We introduce a fully automated judge for semantic similarity that performs well in three semantic similarity tasks at SemEval-2014, Semantic Evaluation Exercises International Workshop on Semantic Evaluation (Nakov and Zesch, 2014). RTMs provide a language independent solution for the semantic textual similarity (STS) task (Task 10) (Agirre et al., 2014), achieve top performance when predicting monolingual cross-level semantic similarity (Task 3) (Jurgens et al., 2014), and achieve good results in the semantic relatedness and entailment task (Task 1) (Marelli et al., 2014a). Referential translation machine (Section 2) is a computational model for identifying the acts of translation for translating between any given two data sets with respect to a reference corpus selected in the same domain. An RTM model is based on the selection of interpretants, training data close to both the training set and the test set, which allow shared semantics by providing context for similarity judgments. In semiotics, an interpretant I interprets the signs used to refer to the real objects (Biçici, 2008). Each RTM model is a data translation and translation prediction model between the instances in the training set and the test set and translation acts are indicators of the data transformation and translation. RTMs present an accurate and language independent solution for making semantic similarity judgments. We describe the tasks we participated below. Section 2 describes the RTM model and the features used. Section 3 presents the training and test results we obtain on the three tasks we competed and the last section concludes. Task 1 Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Entailment (SRE) (Marelli et al., 2014a): Given two sentences, produce a relatedness score indicating the extent to which the sentences express a related meaning: a number in the range [1, 5]. We model the problem as a translation performance prediction task where one possible interpretation is obtained by translating S1 (the source to translate, S) to S2 (the target translation, T). Since linguistic processing can reveal deeper similarity relationships, we also look at the translation task at different granularities of information: plain