论文信息 - Bilingual Terminology Extraction in Sketch Engine

Bilingual Terminology Extraction in Sketch Engine

We present a method of bilingual terminology extraction from parallel corpora and a few heuristics and experiments with improving the performance of the basic variant of the method. An evaluation is given using a small gold standard manually prepared for English-Czech language pair from DGT translation memory. The bilingual terminology extraction (ABTE) is available for several languages in Sketch Engine—the corpus management tool.

Vít Baisa | Barbora Ulipová | Michal Cukr

[1] Pavel Rychlý,et al. A Lexicographer-Friendly Association Score , 2008, RASLAN.

[2] Hendrik Kockaert,et al. Handbook of terminology , 2015 .

[3] Jörg Tiedemann,et al. News from OPUS — A collection of multilingual parallel corpora with tools and interfaces , 2009 .

[4] Takako Aikawa,et al. Automatic validation of terminology translation consistenscy with statistical method , 2007, MTSUMMIT.

[5] Hendrik Kockaert,et al. Handbook of Terminology: Volume 1 , 2015 .

[6] Els Lefever,et al. TExSIS: Bilingual terminology extraction from parallel corpora using chunk-based alignment. , 2013 .

[7] Adam Kilgarriff,et al. Finding Terms in Corpora for Many Languages with the Sketch Engine , 2014, EACL.

[8] Philipp Koehn,et al. Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[9] Ulrich Heid,et al. Extracting terms and their relations from German texts: NLP tools for the preparation of raw material for specialized e-dictionaries , 2015 .

[10] Julian Kupiec,et al. An Algorithm for Finding Noun Phrase Correspondences in Bilingual Corpora , 1993, ACL.

[11] Adam Kilgarriff,et al. The Sketch Engine: ten years on , 2014 .

[12] Andreas Eisele,et al. DGT-TM: A freely available Translation Memory in 22 languages , 2012, LREC.