2005 OnTheSemanticsOfNounCompounds
- (Girju et al., 2005) ⇒ Roxana Girju, Dan Moldovan, Marta Tatu, Daniel Antohe. (2005). “On the Semantics of Noun Compounds.” In: Computer Speech and Language — Special Issue on Multiword Expressions, 19(4). doi:10.1016/j.csl.2005.02.006
Subject Headings: Noun Compound, Lexical Semantics.
Notes
Cited By
Quotes
Abstract
This paper provides new insights on the semantic characteristics of two and three noun compounds. An analysis is performed using two sets of semantic classification categories: a list of 8 prepositional paraphrases previously proposed by Lauer [Designing statistical language learners: experiments on noun compounds, Ph.D. Thesis, Macquarie University, Australia] and a new set of 35 semantic relations introduced by us. We show the distribution of these semantic categories on a corpus of noun compounds and present several models for the bracketing and the semantic classification of noun compounds. The results are compared against state-of-the-art models reported in the literature.
Article Outline
1. Introduction
2. Approach
2.1. Lists of semantic classification relations
2.2. Corpus analysis
2.2.1. The data
2.2.2. Corpus annotation and inter-annotator agreement
2.3. Distribution of semantic relations over the training and test corpora
3. Models for the interpretation of two noun compounds
3.1. Unsupervised probabilistic models
3.2. Supervised models
3.2.1. Semantic scattering
3.2.2. Iterative semantic specialization
3.2.3. Support vector machines
3.3. Experimental results and observations
3.4. Comparison with previous work
4. Models for the interpretation of three noun compounds
4.1. Unsupervised probabilistic models for the bracketing of three noun compounds
4.2. Supervised model for the bracketing and semantic annotation of three noun compounds
4.3. Experimental results and observations
4.3.1. Comparison with previous work
5. Discussion
References
,