We propose a novel unsupervised approach for distinguishing literal and non-literal use of idiomatic expressions. Our model combines an unsupervised and a supervised classifier. The former bases its decision on the cohesive structure of the context and labels training data for the latter, which can then take a larger feature space into account. We show that a combination of both classifiers lea...

This paper proposes a method for constructing a statistical language model with multi word expressions (MWEs) selected from Google Japanese Web N-gram. MWEs are concatenated words that consist of idiomatic expressions or long-length morpheme sequences used frequently. In this paper a method for selecting the effective MWEs that improve the language model based on co-occurrence probabilities of ...

We investigate the effectiveness of different linguistic cues for distinguishing literal and non-literal usages of potentially idiomatic expressions. We focus specifically on features that generalize across different target expressions. While idioms on the whole are frequent, instances of each particular expression can be relatively infrequent and it will often not be feasible to extract and an...

In this paper, we present an application of Genetic Algorithms to extract Multiword Units (i.e. complex lexical units such as compound nouns, idiomatic expressions or phrase templates). For that purpose, a fitness function will be defined whose maximization will serve as a basis for the identification of pertinent word -grams (i.e ordered vectors of words) based on different similarity measures...

This research discusses preliminary efforts to expand the coverage of the PropBank lexicon to multi-word and idiomatic expressions, such as take one for the team. Given overwhelming numbers of such expressions, an efficient way for increasing coverage is needed. This research discusses an approach to adding multiword expressions to the PropBank lexicon in an effective yet semantically rich fash...

We address the problem of classifying multiword expression tokens in running text. We focus our study on Verb-Noun Constructions (VNC) that vary in their idiomaticity depending on context. VNC tokens are classified as either idiomatic or literal. Our approach hinges upon the assumption that a literal VNC will have more in common with its component words than an idiomatic one. Commonality is mea...

Semantic Role Labeling annotation task depends on the correct identification of predicates, before identifying arguments and assigning them role labels. However, most predicates are not constituted only by a verb: they constitute Complex Predicates (CPs) not yet available in a computational lexicon. In order to create a dictionary of CPs, this study employs a corpus-based methodology. Searches ...

Verb–noun idiomatic combinations (VNICs) are idioms consisting of a verb with a noun in its direct object position. Usages of these expressions can be ambiguous between an idiomatic usage and a literal combination. In this paper we propose supervised and unsupervised approaches, based on word embeddings, to identifying token instances of VNICs. Our proposed supervised and unsupervised approache...