Browsing Data Science Institute by Author "Torregrosa, Daniel"
Now showing items 1-4 of 4
-
Back-translation approach for code-switching machine translation: A case study
Masoud, Maraim; Torregrosa, Daniel; Buitelaar, Paul; Arčan, Mihael (AICS2019, 2019-12-05)Recently, machine translation has demonstrated significant progress in terms of translation quality. However, most of the research has focused on translating with pure monolingual texts in the source and the target side ... -
Inferring translation candidates for multilingual dictionary generation with multi-way neural machine translation
Arcan, Mihael; Torregrosa, Daniel; Ahmadi, Sina; McCrae, John P. (National University of Ireland, Galway, 2019-05-20)In the widely-connected digital world, multilingual lexical resources are one of the most important resources, for natural language processing applications, including information retrieval, question answering or knowledge ... -
Leveraging rule-based machine translation knowledge for under-resourced neural machine translation models
Torregrosa, Daniel; Pasricha, Nivranshu; Chakravarth, Bharathi Raja; Masoud, Maraim; Alonso, Juan; Casas, Noe; Arcan, Mihael (NUI Galway, 2019-08-19)Rule-based machine translation is a machine translation paradigm where linguistic knowledge is encoded by an expert in the form of rules that translate from source to target language. While this approach grants total ... -
TIAD 2019 Shared Task: Leveraging knowledge graphs with neural machine translation for automatic multilingual dictionary generation
Torregrosa, Daniel; Arcan, Mihael; Ahmadi, Sina; McCrae, John P. (National University of Ireland, Galway, 2019-04-20)This paper describes the different proposed approaches to the TIAD 2019 Shared Task, which consisted in the automatic discovery and generation of dictionaries leveraging multilingual knowledge bases. We present three methods ...