Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling
By Raphaël Rubino, Flammie A. Pirinen, Miquel Esplà-Gomis, Nikola Ljubesic, Sergio Ortiz Rojas, Vassilis A. Papavassiliou, Prokopis Prokopidis, Antonio Toral. 2015
13 citations recorded by the source corpus.
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.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Philipp Koehn
- Lucia Specia
- Ondrej Bojar
- Barry Haddow
- Christof Monz
- Matt Post
- Varvara Logacheva
- Matteo Negri
Citations in the corpus
- Findings of the 2015 Workshop on Statistical Machine Translation (2015, methodology): “The network was pre-trained by initialising the word lookup-table with distributed word representations, ID Participating team DCU-SHEFF Dublin City University, Ireland and University of Sheffield, UK (Logacheva et al., 2015) HDCL Heidelberg University, Germany (Kreutzer et al., 2015) LORIA Lorraine ”
- Results of the WMT15 Metrics Shared Task (2015, neutral): “In Finnish results, we see again UEDIN - JHU and ABUMATRAN (Rubino et al., 2015) overvalued by BLEU.”