Automatic Noun Phrase Interpretation with Cross-linguistic Evidence
Corina Roxana Girju
Dept of Linguistics
August 31, Thursday, 4-5PM
Lucy Ellis Lounge
The acquisition of semantic knowledge is paramount for any application that requires a deep understanding of natural language text. Motivated by the problem of building a noun phrase-level semantic parser and adapting it to various applications, such as machine translation and multilingual question answering, we present a domain-independent model for noun phrase interpretation. We investigate the problem based on cross-linguistic evidence from a set of five Romance languages: French, Italian, Spanish, Portuguese, and Romanian. The focus on Romance languages is well motivated. Most of the time English noun phrases translate into constructions of the form ''N P N'' in Romance languages where, as we will show, the P (preposition) correlates with the semantics.
Thus, based on two sets of 8 prepositions, and respectively 22 semantic interpretation categories we present empirical observations regarding the distribution of these categories in a cross-lingual corpus and their mapping to various syntactic constructions in English and Romance. Furthermore, given a training set of English noun phrases along with their translations in the five Romance languages, our algorithm automatically learns classification rules and applies them to unseen noun phrase instances for semantic interpretation. Experimental results are compared against two state-of-the-art models reported in the literature.