دورية أكاديمية
Towards a Universal Semantic Dictionary
| العنوان: | Towards a Universal Semantic Dictionary |
|---|---|
| المؤلفون: | Castro-Bleda, Maria Jose, Iklódi, E., Recski, G., Borbély, G. |
| المساهمون: | Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació, Agencia Estatal de Investigación |
| بيانات النشر: | MDPI AG |
| سنة النشر: | 2019 |
| المجموعة: | Universitat Politécnica de Valencia: RiuNet / Politechnical University of Valencia |
| مصطلحات موضوعية: | Natural language processing, Semantics, Word embeddings, Multilingual embeddings, Translation, Artificial neural networks, LENGUAJES Y SISTEMAS INFORMATICOS |
| الوصف: | [EN] A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, multilingual embedding space, is proposed in this paper. Previous approaches learned translation matrices between two specific languages, while this method learns translation matrices between a given language and a shared, multilingual space. The system was first trained on bilingual, and later on multilingual corpora as well. In the first case, two different training data were applied: Dinu¿s English¿Italian benchmark data, and English¿Italian translation pairs extracted from the PanLex database. In the second case, only the PanLex database was used. The system performs on English¿Italian languages with the best setting significantly better than the baseline system given by Mikolov, and it provides a comparable performance with more sophisticated systems. Exploiting the richness of the PanLex database, the proposed method makes it possible to learn linear mappings among an arbitrary number of languages. ; This research was funded by Spanish MINECO and FEDER grant number TIN2017-85854-C4-2-R. ; Castro-Bleda, MJ.; Iklódi, E.; Recski, G.; Borbély, G. (2019). Towards a Universal Semantic Dictionary. Applied Sciences. 9(19):1-14. https://doi.org/10.3390/app9194060Test ; S ; 1 ; 14 ; 9 ; 19 ; Youn, H., Sutton, L., Smith, E., Moore, C., Wilkins, J. F., Maddieson, I., … Bhattacharya, T. (2016). On the universal structure of human lexical semantics. Proceedings of the National Academy of Sciences, 113(7), 1766-1771. doi:10.1073/pnas.1520752113 ; Ruder, S., Vulić, I., & Søgaard, A. (2019). A Survey of Cross-lingual Word Embedding Models. Journal of Artificial Intelligence Research, 65, 569-631. doi:10.1613/jair.1.11640 ; Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017). Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5, 135-146. doi:10.1162/tacl_a_00051 |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| تدمد: | 2076-3417 |
| العلاقة: | Applied Sciences; info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2017-85854-C4-2-R/ES/AMIC-UPV: ANALISIS AFECTIVO DE INFORMACION MULTIMEDIA CON COMUNICACION INCLUSIVA Y NATURAL/; https://doi.org/10.3390/app9194060Test; http://hdl.handle.net/10251/139157Test; urn:eissn:2076-3417 |
| DOI: | 10.3390/app9194060 |
| الإتاحة: | https://doi.org/10.3390/app9194060Test http://hdl.handle.net/10251/139157Test |
| حقوق: | http://creativecommons.org/licenses/by/4.0Test/ ; info:eu-repo/semantics/openAccess |
| رقم الانضمام: | edsbas.7A12D605 |
| قاعدة البيانات: | BASE |
Full Text Finder | تدمد: | 20763417 |
|---|---|
| DOI: | 10.3390/app9194060 |