Translation of Biomedical Documents with Focus on Spanish-English

no code implementations • WS 2018 • Mirela-Stefania Duma, Wolfgang Menzel

For the WMT 2018 shared task of translating documents pertaining to the Biomedical domain, we developed a scoring formula that uses an unsophisticated and effective method of weighting term frequencies and was integrated in a data selection pipeline.

Domain Adaptation Machine Translation +1

Automatic Threshold Detection for Data Selection in Machine Translation

no code implementations • WS 2017 • Mirela-Stefania Duma, Wolfgang Menzel

Domain Adaptation Information Retrieval +2

SEF@UHH at SemEval-2017 Task 1: Unsupervised Knowledge-Free Semantic Textual Similarity via Paragraph Vector

no code implementations • SEMEVAL 2017 • Mirela-Stefania Duma, Wolfgang Menzel

This paper describes our unsupervised knowledge-free approach to the SemEval-2017 Task 1 Competition.

Semantic Similarity Semantic Textual Similarity

Data Selection for IT Texts using Paragraph Vector

no code implementations • WS 2016 • Mirela-Stefania Duma, Wolfgang Menzel

Domain Adaptation Machine Translation