The Role of Modifier and Head Properties in Predicting the Compositionality of English and German Noun-Noun Compounds: A Vector-Space Perspective

Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (*SEM 2016), pages 148–158, Berlin, Germany, August 11-12, 2016. The Role of Modifier and Head Properties in Predicting the Compositionality of English and German Noun-Noun Compounds: A Vector-Space Perspective Sabine Schulte im Walde and Anna H¨atty and Stefan Bott Institut f¨ur Maschinelle Sprachverarbeitung, Universit¨at Stuttgart Pfaffenwaldring 5B, 70569 Stuttgart, Germany {schulte,haettyaa,bottsn}@ims.uni-stuttgart.de Abstract In this paper, we explore the role of con- stituent properties in English and Ger- man noun-noun compounds (corpus fre- quencies of the compounds and their con- stituents; productivity and ambiguity of the constituents; and semantic relations between the constituents), when predict- ing the degrees of compositionality of the compounds within a vector space model. The results demonstrate that the empirical and semantic properties of the compounds and the head nouns play a significant role. 1 Introduction The past 20+ years have witnessed an enormous amount of discussions on whether and how the modifiers and the heads of noun-noun compounds such as butterfly, snowball and teaspoon influence the compositionality of the compounds, i.e., the degree of transparency vs. opaqueness of the com- pounds. The discussions took place mostly in psy- cholinguistic research, typically relying on read- ing time and priming experiments. For example, Sandra (1990) demonstrated in three priming ex- periments that both modifier and head constituents were accessed in semantically transparent En- glish noun-noun compounds (such as teaspoon), but there were no effects for semantically opaque compounds (such as buttercup), when primed ei- ther on their modifier or head constituent. In con- trast, Zwitserlood (1994) provided evidence that the lexical processing system is sensitive to mor- phological complexity independent of semantic transparency. Libben and his colleagues (Libben et al. (1997), Libben et al. (2003)) were the first who systematically categorised noun-noun com- pounds with nominal modifiers and heads into four groups representing all possible combinations of modifier and head transparency (T) vs. opaque- ness (O) within a compound. Examples for these categories were car-wash (TT), strawberry (OT), jailbird (TO), and hogwash (OO). Libben et al. confirmed Zwitserlood’s analyses that both se- mantically transparent and semantically opaque compounds show morphological constituency; in addition, the semantic transparency of the head constituent was found to play a significant role. From a computational point of view, address- ing the compositionality of noun compounds (and multi-word expressions in more general) is a cru- cial ingredient for lexicography and NLP appli- cations, to know whether the expression should be treated as a whole, or through its constituents, and what the expression means. For example, studies such as Cholakov and Kordoni (2014), Weller et al. (2014), Cap et al. (2015), and Salehi et al. (2015b) have integrated the prediction of multi-word compositionality into statistical ma- chine translation. Computational approaches to automatically predict the compositionality of noun compounds have mostly been realised as vector space mod- els, and can be subdivided into two subfields: (i) approaches that aim to predict the meaning of a compound by composite functions, relying on the vectors of the …

Content truncated to 500 words