Relative Compositionality of Multi-word Expressions: A Study of Verb-Noun (V-N) Collocations

Relative Compositionality of Multi-word Expressions: A Study of Verb-Noun (V-N) Collocations Sriram Venkatapathy1,⋆ and Aravind K. Joshi2 1 Language Technologies Research Center, International Institute of Information Technology - Hyderabad, Hyderabad, India sriram@research.iiit.ac.in 2 Department of Computer and Information Science and Institute of Research in Cognitive Science, University of Pennsylvania, Philadelphia, PA, USA joshi@linc.cis.upenn.edu Abstract. Recognition of Multi-word Expressions (MWEs) and their relative compositionality are crucial to Natural Language Processing. Various statistical techniques have been proposed to recognize MWEs. In this paper, we integrate all the existing statistical features and in- vestigate a range of classifiers for their suitability for recognizing the non-compositional Verb-Noun (V-N) collocations. In the task of ranking the V-N collocations based on their relative compositionality, we show that the correlation between the ranks computed by the classifier and hu- man ranking is significantly better than the correlation between ranking of individual features and human ranking. We also show that the prop- erties ‘Distributed frequency of object’ (as defined in [27]) and ‘Nearest Mutual Information’ (as adapted from [18]) contribute greatly to the recognition of the non-compositional MWEs of the V-N type and to the ranking of the V-N collocations based on their relative compositionality. 1 Introduction The main goals of the work presented in this paper are (1) To investigate a range of classifiers for their suitability in recognizing the non-compositional V-N collo- cations, and (2) To examine the relative compositionality of collocations of V-N type. Measuring the relative compositionality of V-N collocations is extremely helpful in applications such as machine translation where the collocations that are highly non-compositional can be handled in a special way. Multi-word expressions (MWEs) are those whose structure and meaning can- not be derived from their component words, as they occur independently. Ex- amples include conjunctions like ‘as well as’ (meaning ‘including’), idioms like ⋆ Part of the work was done at Institute for Research in Cognitive Science, University of Pennsylvania, Philadelphia, PA 19104, USA, when he was visiting IRCS as a visiting Scholar, February to December, 2004. R. Dale et al. (Eds.): IJCNLP 2005, LNAI 3651, pp. 553–564, 2005. c ⃝ Springer-Verlag Berlin Heidelberg 2005 554 S. Venkatapathy and A.K. Joshi ‘kick the bucket’ (meaning ‘die’), phrasal verbs like ‘find out’ (meaning ‘search’) and compounds like ‘village community’. A typical natural language system as- sumes each word to be a lexical unit, but this assumption does not hold in case of MWEs [6] [12]. They have idiosyncratic interpretations which cross word boundaries and hence are a ‘pain in the neck’ [23]. They account for a large portion of the language used in day-to-day interactions [25] and so, handling them becomes an important task. A large number of MWEs have a standard syntactic structure but are non- compositional semantically. An example of such a subset is the class of non- compositional verb-noun collocations (V-N collocations). The class of V-N col- locations which are non-compositional is important because they are used very frequently. These include verbal idioms [22], support-verb constructions [1] [2] etc. …

Content truncated to 500 words