Referential translation machines for predicting semantic similarity

Abstract

Referential translation machines (RTMs) are a computational model effective at judging monolingual and bilingual similarity while identifying translation acts between any two data sets with respect to interpretants, data close to the task instances. RTMs pioneer a language-independent approach to all similarity tasks and remove the need to access any task- or domain-specific information or resource. We use RTMs for predicting the semantic similarity of text and present state-of-the-art results showing that RTMs can achieve better results on the test set than on the training set. Interpretants are used to derive features measuring the closeness of the test sentences to the training data, the difficulty of translating them, and the presence of the acts of translation, which may ubiquitously be observed in communication. RTMs can achieve top performance at SemEval in various semantic similarity prediction tasks as well as similarity prediction tasks in bilingual settings. We obtain rankings of various prediction tasks using the performance of RTM and relative evaluation metrics, which can help identify which tasks and subtasks require more work by design.