Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling

Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 184–191, Lisboa, Portugal, 17-18 September 2015. c⃝2015 Association for Computational Linguistics. Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling Raphael Rubino⋆, Tommi Pirinen†, Miquel Espl`a-Gomis‡, Nikola Ljubeˇsi´cγ, Sergio Ortiz-Rojas⋆, Vassilis Papavassiliou♮, Prokopis Prokopidis♮, Antonio Toral† ⋆ Prompsit Language Engineering, S.L., Elche, Spain {rrubino,sortiz}@prompsit.com † NCLT, School of Computing, Dublin City University, Ireland {atoral,tpirinen}@computing.dcu.ie ‡ Dep. Llenguatges i Sistemes Inform`atics, Universitat d’Alacant, Spain mespla@dlsi.ua.es γ Department of Information and Communication Sciences, University of Zagreb, Croatia nljubesi@ffzg.hr ♮ Institute for Language and Speech Processing, Athena Research and Innovation Center, Greece {vpapa, prokopis}@ilsp.gr Abstract This paper presents the machine transla- tion 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 morpholog- ical segmentation. Several statistical ma- chine translation approaches are evaluated and then combined to obtain our final sub- missions, which are the top performing English-to-Finnish unconstrained (all au- tomatic metrics) and constrained (BLEU), and Finnish-to-English constrained (TER) systems. 1 Introduction This paper presents the statistical machine transla- tion (SMT) systems submitted by the Abu-MaTran project for the WMT 2015 translation task. The language pair concerned is Finnish–English with a strong focus on the English-to-Finnish direction. The Finnish language is newly introduced this year as a particular translation challenge due to its rich morphology and to the lack of resources available, compared to e.g. English or French. Morphologically rich languages, and especially Finnish, are known to be difficult to translate us- ing phrase-based SMT systems mainly because of the large diversity of word forms leading to data scarcity (Koehn, 2005). We assume that data acqui- sition and morphological segmentation should con- tribute to decrease the out-of-vocabulary rate and thus improve the performance of SMT. To gather additional data, we decide to build on previous work conducted in the Abu-MaTran project and crawl the Web looking for monolingual and paral- lel corpora (Toral et al., 2014). In addition, mor- phological segmentation of Finnish is used in our systems as pre- and post-processing steps. Four segmentation methods are proposed in this paper, two unsupervised and two rule-based. Both constrained and unconstrained translation systems are submitted for the shared task. The former ones are trained on the data provided by the shared task, while the latter ones benefit from crawled data. For both settings, we evaluate the im- pact of the different SMT approaches and morpho- logical segmentation methods. Finally, the outputs of individually trained systems are combined to obtain our primary submissions for the translation tasks. This paper is structured as follows: the methods for data acquisition from the Web are described in Section 2. Morphological segmentation is pre- sented in Section 3. The data and tools used in our experiments are detailed in Section 4. Finally, the results of our experiments are …

Content truncated to 500 words