On the interpretation of noun compounds: Syntax, semantics, and entailment

Abstract

We discuss the problem of interpreting noun compounds such as colon cancer tumor suppressor protein, which pose major challenges for the automatic interpretation of English written text. We present an overview of the more general process of compounding and of noun compounds in particular, as well as of their syntax and semantics from both theoretical and computational linguistics viewpoint with an emphasis on the latter. Our main focus is on computational approaches to the syntax and semantics of noun compounds: we describe the problems, present the challenges, and discuss the most important lines of research. We also show how understanding noun compound syntax and semantics could help solve textual entailment problems, which would be potentially useful for a number of NLP applications, and which we believe to be an important direction for future research.

Multiword noun compound bracketing using Wikipedia

“…Lastly, similarly to other researchers who look at noun compound bracketing as the first step of semantic analysis of NPs to elicit semantic relations (purpose, cause, location, etc) between subgroups of words (Girju et al (2005), Nastase et al (2013)), we want to pursue our work into a more fine-grained understanding of noun compounds (Nakov, 2013), combining bracketing with the identification of specific noun relations.…”

“…We make the assumption that dependencies are implicitly directed left-to-right. This is an oversimplification, as there are a few cases, such as Vitamin C or Cafe Vienna, pointed in (Nakov, 2013), where the direction is reversed. Furthermore, this hypothesis is valid only for English and renders our algorithm less applicable to other languages.…”

Semantic interpretation of noun compounds using verbal and other paraphrases

“…Such coarse-grained relations can in turn be helpful for other applications, e.g., for recognizing textual entailment as shown by Tatu and Moldovan [2005]. Note however, that, for this task, it is possible to use our noun compound paraphrasing verbs directly; for details, see [Nakov 2013] or Appendix B of [Nakov 2007].…”

Semantic annotation to characterize contextual variation in terminological noun compounds: a pilot study

“…In English, noun compounds (NCs) are the lexical units that are most often used to convey expert knowledge (Daille et al, 2004;Nakov, 2013;Hendrickx et al, 2013). Terminological NCs can be considered a type of multi-word term (MWT) because they are non-idiomatic multi-word units that belong to a specialized domain and lie in the intersection between terms and multi-word expressions (MWEs) (SanJuan et al, 2005;Frantzi et al, 2000;Ramisch, 2015).…”