The goal of paraphrase identification is to decide whether two given text fragments have the same meaning. Of particular interest in this area is the identification of paraphrases among short texts, such as SMS and Twitter. In this paper, we present idiomatic expressions as a new domain for short-text paraphrase identification. We propose a technique, utilizing idiom definitions and continuous ...

Support-verb constructions (i.e., multiword expressions combining a semantically light verb with a predicative noun) are problematic for standard statistical machine translation systems, because SMT systems cannot distinguish between literal and idiomatic uses of the verb. We work on the German to English translation direction, for which the identification of support-verb constructions is chall...

Hierarchical lexicon structures are not only of great importance for the nonredundant representation of lexical information, they may also contribute to the efficiency of the actual processing of natural language. Two parsing techniques that render the parsing process efficient are presented. Windowing is a technique for incrementally accessing the hierarchical lexicon. Lexical preferencing imp...

The aim of this study is to identify idiomatic expressions in English using the measure perplexity. assumption that cause higher perplexity than literal given a reference text. Perplexity our calculated based on n-grams (i) PoS tags, (ii) tokens, and (iii) thematic roles within boundaries sentence. In setting study, we observed no contexts (i), manages distinguish from literals. We postulate la...

In this paper, we describe the binary classification of sentences into idiomatic and non-idiomatic. Our idiom detection algorithm is based on linear discriminant analysis (LDA). To obtain a discriminant subspace, we train our model on a small number of randomly selected idiomatic and non-idiomatic sentences. We then project both the training and the test data on the chosen subspace and use the ...

Treatment of Multiword Expressions (MWEs) is one of the most complicated issues in natural language processing, especially in Machine Translation (MT). The paper presents dictionary of MWEs for a English-Latvian MT system, demonstrating a way how MWEs could be handled for inflected languages with rich morphology and rather free word order. The proposed dictionary of MWEs consists of two constit...

Using cross-modal priming, we investigated the processing of idioms in non-native listeners in varying experimental contexts. As idiomatic processing models have presented evidence for an idiomatic mode of processing that can be activated for non-native speakers in highly figurative contexts (Bobrow & Bell, 1973), this experiment revisits those claims while also examining access to figurative m...

Several studies of L2 learners’ interlanguage have addressed the complexity of the English adpositional system due to several reasons like L1 transfer, lack of knowledge in L2 and the strong collocational relations of prepositions with other elements of the English language. The major purpose of the present study is to evaluate the performance of Iranian students in dealing with three broad cat...