Polish - English Speech Statistical Machine Translation Systems for the IWSLT 2013
This work addresses translation quality for Polish-English spoken language, but appears incremental as it focuses on standard SMT techniques and data preparation.
The researchers investigated how different training configurations affect Polish-to-English statistical machine translation for spoken language, using TED corpus data from IWSLT 2013 and evaluating with metrics like BLEU and TER, but no specific numerical results were reported in the abstract.
This research explores the effects of various training settings from Polish to English Statistical Machine Translation system for spoken language. Various elements of the TED parallel text corpora for the IWSLT 2013 evaluation campaign were used as the basis for training of language models, and for development, tuning and testing of the translation system. The BLEU, NIST, METEOR and TER metrics were used to evaluate the effects of data preparations on translation results. Our experiments included systems, which use stems and morphological information on Polish words. We also conducted a deep analysis of provided Polish data as preparatory work for the automatic data correction and cleaning phase.