Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling
Autor: | Raphael Rubino, Tommi A. Pirinen, Miquel Esplà-Gomis, Prokopis Prokopidis, Vassilis Papavassiliou, Sergio Ortiz Rojas, Antonio Toral, Nikola Ljubešić |
---|---|
Rok vydání: | 2015 |
Předmět: |
Machine translation
business.industry Computer science Crawling Translation (geometry) computer.software_genre Machine learning Task (project management) Rule-based machine translation Artificial intelligence Evaluation of machine translation business Web crawler computer Morphological segmentation Natural language processing |
Zdroj: | WMT@EMNLP |
Popis: | This paper presents the machine translation systems submitted by the Abu-MaTran project for the Finnish‐English language pair at the WMT 2015 translation task. We tackle the lack of resources and complex morphology of the Finnish language by (i) crawling parallel and monolingual data from the Web and (ii) applying rule-based and unsupervised methods for morphological segmentation. Several statistical machine translation approaches are evaluated and then combined to obtain our final submissions, which are the top performing English-to-Finnish unconstrained (all automatic metrics) and constrained (BLEU), and Finnish-to-English constrained (TER) systems. |
Databáze: | OpenAIRE |
Externí odkaz: |