Idiom token classification is the task of deciding for a set of potentially idiomatic phrases whether each occurrence of a phrase is a literal or idiomatic usage of the phrase. In this work we explore the use of Skip-Thought Vectors to create distributed representations that encode features that are predictive with respect to idiom token classification. We show that classifiers using these repr...

Idioms are sometimes viewed as unitized phrases with interpretations that are independent of the literal meanings of their individual words. In three experiments, the nature of idiom representation was explored with a speech-error elicitation task. In the task, speakers briefly viewed paired idioms. After a short delay they were probed to produce one of the two idioms, and their production late...

The findings of a study that explored the beliefs, assumptions and ideas nurses have about the coping of patients are presented. Interactive interviews with 26 nurses were used to elicit explanations of the meaning of coping and stories from their practice that illustrated coping. Analysis of the interview transcripts revealed three themes in the form of idioms or particular and different ways ...

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 ...

The ability to understand ambiguous idiom was assessed in aphasic patients with preserved comprehension at a single word level. A string-to-word matching task was used in which patients were requested to choose one among four alternatives: a word associated with the figurative meaning of the idiom string; a word semantically associate with the last constituent of the idiom string; and two unrel...

A standard view is that idioms present problems for compositionality. The question of compositionality, however, should be posed for a semantics, not for individual phrases. The paper focuses on the idiom extension problem: Suppose in a given language a certain phrase acquires the status of an idiom. How can the syntax and semantics be extended to accommodate the idiom, while preserving desirab...

This study investigated the comparative effect of teaching idiomatic expressions through practicing them in conversation and paragraph writing on intermediate EFL learners’ idiom learning. The participants were sorted out of a population of 134 intermediate students in Zabansara Language School in Khorramabad based on their scores on a Preliminary English Test (PET) and an idiom test piloted in...

This paper describes work towards the goal of enabling unscripted interaction with non-player characters in virtual environments. We hypothesize that we can define a layer of social affordances, based on physical and non-verbal signals exchanged between individuals and groups, which can be reused across games. We have implemented a first version of that substrate that employs whole body interac...

Models of idiom comprehension differ in their predictions concerning compositionality: Some claim that idiomatic meaning is the result of compositional analysis initiated at the earliest stages of comprehension, whereas others claim that compositional analysis occurs only at late stages, subsequent to direct retrieval--especially for idioms that are highly familiar. We evaluated these alternati...