Paraphrasing Compound Nominalizations

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8023–8028 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 8023 Paraphrasing Compound Nominalizations John S. Y. Lee, Ho Hung Lim Department of Linguistics and Translation City University of Hong Kong Hong Kong SAR, China jsylee@cityu.edu.hk hhlim3@cityu.edu.hk Carol Webster College of Professional and Continuing Education The Hong Kong Polytechnic University Hong Kong SAR, China carol.webster@cpce-polyu.edu.hk Abstract A nominalization uses a deverbal noun to de- scribe an event associated with its underlying verb. Commonly found in academic and for- mal texts, nominalizations can be difficult to interpret because of ambiguous semantic re- lations between the deverbal noun and its ar- guments. Our goal is to interpret nominaliza- tions by generating clausal paraphrases. We address compound nominalizations with both nominal and adjectival modifiers, as well as prepositional phrases. In evaluations on a num- ber of unsupervised methods, we obtained the strongest performance by using a pre-trained contextualized language model to re-rank para- phrase candidates identified by a textual entail- ment model. 1 Introduction Nominalizations are widely used in academic and other genres of formal texts that adopt a com- pact and abstract writing style. A nominalization is a noun (e.g., “treatment”) that is morphologi- cally derived from a verb (“treat”), and that desig- nates some aspects of the event referred to by the verb (Quirk et al., 1985). Because of the systematic correspondence between nominalization and clause structure, a noun phrase headed by a deverbal noun (e.g., “surgical treatment of fracture”) often has a clausal paraphrase headed by the underlying verb (“the surgery treats fracture”) (Cohen et al., 2008). This paper aims to generate clausal paraphrases for nominalizations. A key requirement in this task is to map the arguments of the deverbal noun to those of the underlying verb. In the example above, the deverbal noun “treatment” has a prepositional phrase (PP) argument (“of fracture”) that corre- sponds to the object of the verb “treat”, while the prenominal modifier (“surgical”) corresponds to the subject. This mapping varies according to the semantic context of the nominalization. An alter- native nominalization, such as “fracture treatment with surgery”, may have its PP argument (“with surgery”) mapped to the subject, and its prenominal modifier (“fracture”) mapped to the object. Table 1 shows a range of possible mappings. Our task is distinguished from previous research in terms of both the input and output. In the field of nominalization disambiguation, most studies have focused on deverbal nouns with one argument, typ- ically a nominal modifier (Lapata, 2002; Nicholson and Baldwin, 2008). We extend the scope by ad- dressing both nominal and adjectival modifiers, as well as PP argument. In terms of the output, most previous work as- signed semantic role labels to arguments of the de- verbal noun; in contrast, we generate paraphrases in predicate-argument form (Table 1). This approach has the advantage of avoiding commitment to a particular semantic theory, and can facilitate direct application to various NLP downstream tasks. The paraphrases may improve performance …

Content truncated to 500 words