| Programa general, fitxa d'activitat
|
|
| |
|
|
|
Dijous 28 d'abril de 2016 13:00 a 13:30 |
|
Comunicación |
Exploring the semantics of multi-word terms by means of paraphrases Exposa: Melania Isabel Cabezas García, Universidad de Granada
Multi-word terms (MWTs) in the form of noun compounds are the main way that concepts are linguistically expressed in specialized domains. The disambiguation of these juxtaposed terms varies, depending on the previously stored knowledge of the receiver. Another aspect to be considered is the fact that each language has its own term formation patterns. Therefore accessing the semantic content of MWTs with a certain level of accuracy is the first step to understanding and translating them.
Until now, most studies have focused on two-term compounds (Kim & Baldwin 2013), in particular, when devising methods for recognising and automatically extracting them from a corpus. This paper, however, describes the syntax and semantics of English and Spanish endocentric noun compounds in the specialized domain of Coastal Engineering with a view to formulating mapping relations between English terms and their Spanish correspondences.
The terms in our study were extracted from the Ecolexicon corpus (http://ecolexicon.ugr.es/) and designate processes. They represent compressed propositions whose implicit conceptual relationship must be recovered by an audience. This study also focused on the role of micro-contexts in term formation (Hendrickx et al. 2013) and the hypothesis that compounds formed by similar terms usually have the same semantic relation (Kim & Baldwin 2013).
Our analysis involved parsing and bracketing, in order to specify the semantic structure and dependencies of the MWTs. Semantic relations were then assigned (see Nastase and Szpakowicz 2003) and meaning of the MWTs was expanded through paraphrasing (Nakov 2013). Finally, the paraphrases produced by Coastal Engineering experts were compared with those extracted from web search engines.
Our results showed that a predicate-based analysis facilitated the specification of the relations between the concepts in MWTs as well as the mapping of this content onto the corresponding term in the target language.
References
Hendrickx, I., Kozareva, Z., Nakov, P., Séaghdha, D. O., Szpakowicz, S. & Veale, T. (2013). SemEval-2013 task 4: Free paraphrases of noun compounds. In Proceedings of the International Workshop on Semantic Evaluation. SemEval ’13. 138-143. Atlanta: Association for Computational Linguistics.
Kim, S. N. & Baldwin, T. (2013). A lexical semantic approach to interpreting and bracketing English noun compounds. Natural Language Engineering, 19, 385-407.
Nakov, P. (2013). On the interpretation of noun compounds: Syntax, semantics, and entailment. Natural Language Engineering, 19, 291-330.
Nastase, V. & Szpakowicz, S. (2003). Exploring noun-modifier semantic relations. In Fifth International Workshop on Computational Semantics. IWCS ’03. 285–301. Tilburg. Més informació: Topic 1 Lingüística aplicada a la traducció: discurs, lèxic, terminologia, corpus
|