Transplanting supertags from English to Spanish
نویسنده
چکیده
In this paper, we present an approach to quickly develop supertags for a target language given supertags for another language (reference language), along with a sentence-aligned parallel corpus between reference language and target language pairs. Our method can be interpreted as composing the alignment relation with dependency relation of the reference sentence to obtain the dependency relation for the target sentence. This dependency relation is then used to induce the supertags for the target words.
منابع مشابه
Cultural Influence on the Expression of Cathartic Conceptualization in English and Spanish: A Corpus-Based Analysis
This paper investigates the conceptualization of emotional release from a cognitive linguistics perspective (Cognitive Metaphor Theory). The metaphor weeping is a means of liberating contained emotions is grounded in universal embodied cognition and is reflected in linguistic expressions in English and Spanish. Lexicalization patterns which encapsulate this conceptualization i...
متن کاملA Pragmatic Study of Speech Acts by Iranian and Spanish Nonnative English Learners
This study was an attempt to investigate Iranian and Spanish intermediate nonnative English learners’ request strategies to their faculty. To this aim, 74 (50 Iranian and 24 Spanish) nonnative English intermediate learners participated in this study. A discourse completion test (DCT) was used to elicit the request strategies used by the participants. The findings suggested the participants empl...
متن کاملExtracting LTAG Grammars from a Spanish Treebank
Treebank grammars have been known to help in building robust, wide-coverage statistical parsers that also obtain state-of-art accuracies. In this work, we present a system that extracts LTAG grammars for Spanish from a constituency-based Spanish treebank. We evaluate the extracted grammar in terms of its size, its coverage on unseen data and the performance of a supertagger trained on it. The s...
متن کاملPredicting Target Language CCG Supertags Improves Neural Machine Translation
Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) Does explicitly modeling target language syntax help NMT? 2) Is tight integration of words and syntax better than multitask tra...
متن کاملDisagreement and Degrees of Assertiveness in Service Encounters: Purchase vs Problem-Solving Interactions
This paper examined disagreement in two sets of data in the context of service encounters: problem-solving interactions (doctor-patient communication) and purchase-oriented encounters (pharmacies) from a cross-cultural perspective (Spanish-British English). We proposed assertiveness, a term that refers to both socio-psychological and linguistic features of communication, as a concept that may h...
متن کامل