Jody Foo

Publications

• Terminology Extraction and Term Ranking for Standardizing Term Banks

  Magnus Merkel, Jody Foo

  Proceedings of the 16th Nordic Conference of Computational Linguistics NODALIDA-2007. Editors: Joakim Nivre, Heiki-Jaan Kaalep, Kadri Muischnek and Mare Koit. University of Tartu, Tartu, 2007. ISBN 978-9985-4-0513-0 (online) ISBN 978-9985-4-0514-7 (CD-ROM) pp. 349-354.... [more] Proceedings of the 16th Nordic Conference of Computational Linguistics NODALIDA-2007. Editors: Joakim Nivre, Heiki-Jaan Kaalep, Kadri Muischnek and Mare Koit. University of Tartu, Tartu, 2007. ISBN 978-9985-4-0513-0 (online) ISBN 978-9985-4-0514-7 (CD-ROM) pp. 349-354.

• Terminology extraction and term ranking for standardizing term banks

  Merkel M., Foo J.

  NODALIDA 07, Tartu, Estonia;

  This paper presents how word alignment techniques could be used for building standardized term banks. It is shown that time and effort could be saved by a relatively simple evaluation metric based on frequency data from term pairs, and source and target distributions inside the alignment results. Th... [more] This paper presents how word alignment techniques could be used for building standardized term banks. It is shown that time and effort could be saved by a relatively simple evaluation metric based on frequency data from term pairs, and source and target distributions inside the alignment results. The proposed Q-value metric is shown to outperform other tested metrics such as Dice’s coefficient, and simple pair frequency.

• Computer aided term bank creation and standardization — Building standardized term banks through automated term extraction and advanced editing tools

  Foo, M. J. Merkel

  Terminology in Society, Antwerp, Belgium;

  Using a standardized term bank in both authoring and translation processes can assure that consistent terminology is present, which minimizes textual inconsistencies as well as confusion and frustration from the readers. One of the biggest problems of creating a standardized term bank is the amount ... [more] Using a standardized term bank in both authoring and translation processes can assure that consistent terminology is present, which minimizes textual inconsistencies as well as confusion and frustration from the readers. One of the biggest problems of creating a standardized term bank is the amount of manual labor needed. Recent development of term extraction techniques based on word alignment, can greatly improve extraction of term candidates when parallel texts are available. Even if the word alignment method used produces a 100 per cent accurate map between the source and target texts, the total set of extracted term candidates still need manual analysis to select which candidates should be promoted to standardized terms. To minimize the work needed in the post extraction phase of building a standardized term bank, we propose a method based on using efficient editing tools, as well as trying to rank the extracted set of term candidates by quality or relevance. This sorted set of term candidates can then be edited, categorized and filtered in a much more effective way. In this paper, the process and methods used to arrive at a standardized term bank are presented and discussed.