Citation Context

... distinguishing between idiomatic and literal usages of such expressions, and indeed there have recently been several studies addressing this issue (Birke and Sarkar, 2006; Katz and Giesbrecht, 2006; =-=Cook et al., 2007-=-). In order to conduct further research on VNCs at the token level, and to compare the effectiveness of the varying proposed methods for their treatment, an annotated corpus of VNC usages is required....

Citation Context

...We explore several vector similarity metrics. We exploit more linguistically oriented feature sets to model the VNC vector space. We evaluate our results against a standard data set from the study by =-=[10]-=-. We achieve state of the art performance in classifying VNC tokens as either literal (F-measure: Fβ1=0.69) or idiomatic (Fβ1=0.83), corresponding to an overall accuracy of 77.56%. Recognizing the gra...

Citation Context

...es on selectional preferences for both the noun and the verb and they also make use of automatic noun clustering when considering the selection of semantic classes of nouns for each verb. Cook et al. =-=[4]-=- differentiate between literal and idiomatic usages of verb and noun constructions in English. Their basic hypothesis is that Identifying verbal collocations in Wikipedia articles 3 the canonical form...

Citation Context

... computational works on LVCs , if related to token-based identification, i.e., identifying idiomatic expressions within context, only consider LVCs as one small subtype of other idiomatic expressions =-=[39, 40]-=-. In addition, previous computational works on token-based identification differs from our work in one key aspect. Our work builds a learning system which systematically incorporates both informative ...

Citation Context

...or multiple-word) lexical items. Usually, these are nominal lexical items that denote concrete or abstract entities. The most straight-forward strategy for term identification is a look up in existing terminological dictionaries. In recent research, this strategy has a poor reputation because it is prone to scaling limitations due to neologisms, lexical variation, synonymy, etc., which make the terminology be submitted to a constant change [15]. As an alternative, a number of works cast syntactic and/or semantic criteria into rules to determine whether a given lexical item qualifies as a term [3, 4, 7], while others apply the statistical criterion of relative frequency of an item in a domain-specific corpus; see, for example, [1, 10, 22, 24, 25]. Most often, state-of-the-art statistical term identification is preceded by a rule-based stage in which the preselection of term candidates is done drawing upon linguistic criteria. However, most of the state-of-the-art proposals neglect that a new generation of terminological (and thus conceptual) resources emerged and with them, instruments to keep these resources updated. 1 NLP Group, Pompeu Fabra University, Barcelona, email: joan.codina@upf.ed...

Citation Context

... and human judges annotate a whole sentence instead of only the MWE candidate. Data sets of sentences with token-level MWE annotations include, for example, English idiomatic verb-noun constructions (=-=Cook et al. 2007-=-; 2008), English verb-particle constructions (Baldwin 2008), and German verb-preposition-noun constructions (Fritzinger et al. 2010). 4.1.2 Evaluation measures The intrinsic quantitative evaluation of...