There is a construction in English, exemplified by how long a bridge, which is so irregular that it has been named the Big Mess Construction, see Berman (1974). This paper first sketches its main characteristics (section 1) and a treatment of the internal structure of the noun phrase which serves as a background for the analysis (section 2). It then presents three ways in which the Big Mess Con...

This paper proposes an unsupervised approach to automatically interpret noun compounds using semantic similarity. Our proposed unsupervised method is based on obtaining a large amount of robust evidence for NC interpretation. In order to obtain evidence sentences for semantic relations (SRs), we first acquired sentences containing both a head noun and its modifier in the form of SR definitions....

This paper shows that linguistic techniques along with machine learning can extract high quality noun phrases for the purpose of providing the gist or summary of email messages. We describe a set of comparative experiments using several machine learning algorithms for the task of salient noun phrase extraction. Three main conclusions can be drawn from this study: (i) the modifiers of a noun phr...

In this paper we present our system for the SemEval 2013 Task 5a on semantic similarity of words and compositional phrases. Our system uses a dependency-based vector space model, in combination with a technique called latent vector weighting. The system computes the similarity between a particular noun instance and the head noun of a particular noun phrase, which was weighted according to the s...

The discovery of semantic relations in text plays an important role in many NLP applications. This paper presents a method for the automatic classification of semantic relations in nominalized noun phrases. Nominalizations represent a subclass of NP constructions in which either the head or the modifier noun is derived from a verb while the other noun is an argument of this verb. Especially des...

Data from Hebrew have been claimed to support the hypothesis that noun phrases should be considered DPs universally. This paper shows that the application of the DP hypothesis to Hebrew is based on partial data and theory-internal considerations. A straightforward analysis of noun phrases as NPs is proposed ; it is shown to account for a variety of facts that were believed to necessitate the in...

Abstract Extraction of a PP from an NP in German is possible only if the head noun and governing verb together form natural predicate. We show that this corresponds to collocational frequency verb-noun combinations corpora, based on metric Δ P . From we conclude should be conceived as language-external grammatical building block can directly interact with language-internal blocks (like triggers...

This chapter describes nominal constructions in the Central variety of Taleshi (Northwestern Iranian). In Taleshi, noun phrases and majority adpositional are head-final. Some modifiers as well complement postpositions linked to head phrase by a linking element––known Reverse Ezafe (Stilo 2004). this chapter, we show that appearing with possessors adpositions is different from attributive adject...

In this paper, we present an analysis of noun phrases with elided nouns that dispenses with the positing of empty categories and preserves the NP structure assumed for NPs with overt nouns, modulo the absence of the head noun. On a par with traceless analyses of long distance dependencies, this is proposed as a further step towards a more lean theory of grammar, without phonetically null items.

In this paper, we explore the role of constituent properties in English and German noun-noun compounds (corpus frequencies of the compounds and their constituents; productivity and ambiguity of the constituents; and semantic relations between the constituents), when predicting the degrees of compositionality of the compounds within a vector space model. The results demonstrate that the empirica...