Building a supertagger for Spanish HPSG. (March 2019)

• Record Type: Journal Article
• Authors: Chiruzzo, Luis; Wonsever, Dina
• Is Part Of: Computer speech & language. Volume 54(2019)
• Page Start: 44
• Page End: 60
• Publication Date: 2019-03
• Subjects: HPSG -- Supertagging -- Parsing -- Spanish -- Lexical frames -- Word embeddings; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2018.08.005
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: We created a supertagger for Spanish HPSG. The supertagger classifies lexical frames for verbs, nouns and adjectives. The accuracy of the supertagger is 84% for verbs, 86% for nouns and 91% for adjectives considering the top three tags. The supertagger uses lemmas, POS and word embeddings as training features. Abstract: We created a supertagger for the Spanish language aimed at disambiguating the HPSG lexical frames for the verbs, nouns and adjectives in a sentence. The supertagger uses a maximum entropy model and achieves an accuracy of 84.16% over the verb classes, 86.60% over the noun classes and 91.30% over the adjective classes on the test set. The tagset contains 92 verb classes, 27 noun classes and 13 adjective classes extracted from a Spanish HPSG-compatible annotated corpus that was created by automatically transforming the AnCora Spanish corpus. The tags include information about the arguments structure, their syntactic categories and semantic roles. These are important pieces of HPSG style feature structures.