Semantic Role Assignment for Event Nominalisations by Leveraging Verbal Data

Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 665–672 Manchester, August 2008 Semantic role assignment for event nominalisations by leveraging verbal data Sebastian Pad´o Department of Linguistics Stanford University 450 Serra Mall Stanford CA 94305, USA pado@stanford.edu Marco Pennacchiotti and Caroline Sporleder Computational Linguistics Saarland University Postfach 15 11 50 66041 Saarbr¨ucken, Germany {pennacchiotti|csporled}@coli.uni-sb.de Abstract This paper presents a novel approach to the task of semantic role labelling for event nominalisations, which make up a consider- able fraction of predicates in running text, but are underrepresented in terms of train- ing data and difficult to model. We propose to address this situation by data expansion. We construct a model for nominal role la- belling solely from verbal training data. The best quality results from salvaging gram- matical features where applicable, and gen- eralising over lexical heads otherwise. 1 Introduction The last years have seen a large body of work on modelling the semantic properties of individual words, both in the form of hand-built resources like WordNet and data-driven methods like seman- tic space models. It is still much less clear how the combined meaning of phrases can be described. Semantic roles describe an important aspect of phrasal meaning by characterising the relationship between predicates and their arguments on a seman- tic level (e.g., agent, patient). They generalise over surface categories (such as subject, object) and vari- ations (such as diathesis alternations). Two frame- works for semantic roles have found wide use in the community, PropBank (Palmer et al., 2005) and FrameNet (Fillmore et al., 2003). Their corpora are used to train supervised models for semantic role labelling (SRL) of new text (Gildea and Jurafsky, 2002; Carreras and M`arquez, 2005). The resulting analysis can benefit a number of applications, such c⃝ 2008. Licensed under the Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported license (http://creativecommons.org/licenses/by-nc-sa/3.0/). Some rights reserved. as Information Extraction (Moschitti et al., 2003) or Question Answering (Frank et al., 2007). A commonly encountered criticism of seman- tic roles, and arguably a major obstacle to their adoption in NLP, is their limited coverage. Since manual semantic role tagging is costly, it is hardly conceivable that gold standard annotation will ulti- mately be available for every predicate of English. In addition, the lexically specific nature of the map- ping between surface syntax and semantic roles makes it difficult to generalise from seen predicates to unseen predicates for which no training data is available. Techniques for extending the coverage of SRL therefore address an important need. Unfortunately, pioneering work in unsupervised SRL (Swier and Stevenson, 2004; Grenager and Manning, 2006) currently either relies on a small number of semantic roles, or cannot identify equiva- lent roles across predicates. A promising alternative direction is automatic data expansion, i.e., lever- aging existing annotations to classify unseen, but similar, predicates. The feasibility of this approach was demonstrated by Gordon and Swanson (2007) for syntactically similar verbs. However, their ap- proach requires at least one annotated instance of each new predicate, limiting its practicability. …

Content truncated to 500 words