Two methods using comparable corpora to select translation equivalents appropriate to a domain were devised and evaluated. The first method ranks translation equivalents of a target word according to similarity of their contexts to that of the target word. The second method ranks translation equivalents according to the ratio of associated words that suggest them. An experiment using the EDR bilingual dictionary together with Wall Street Journal and Nihon Keizai Shimbun corpora showed that the method using the ratio of associated words outperforms the method based on contextual similarity. Namely, in a quantitative evaluation using pseudo words, the maximum F-measure of the former method was 86%, while that of the latter method was 82%. The key feature of the method using the ratio of associated words is that it outputs selected translation equivalents together with representative associated words, enabling the translation equivalents to be validated.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hiroyuki KAJI, "Adapting a Bilingual Dictionary to Domains" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 2, pp. 302-312, February 2005, doi: 10.1093/ietisy/e88-d.2.302.
Abstract: Two methods using comparable corpora to select translation equivalents appropriate to a domain were devised and evaluated. The first method ranks translation equivalents of a target word according to similarity of their contexts to that of the target word. The second method ranks translation equivalents according to the ratio of associated words that suggest them. An experiment using the EDR bilingual dictionary together with Wall Street Journal and Nihon Keizai Shimbun corpora showed that the method using the ratio of associated words outperforms the method based on contextual similarity. Namely, in a quantitative evaluation using pseudo words, the maximum F-measure of the former method was 86%, while that of the latter method was 82%. The key feature of the method using the ratio of associated words is that it outputs selected translation equivalents together with representative associated words, enabling the translation equivalents to be validated.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.2.302/_p
Copy
@ARTICLE{e88-d_2_302,
author={Hiroyuki KAJI, },
journal={IEICE TRANSACTIONS on Information},
title={Adapting a Bilingual Dictionary to Domains},
year={2005},
volume={E88-D},
number={2},
pages={302-312},
abstract={Two methods using comparable corpora to select translation equivalents appropriate to a domain were devised and evaluated. The first method ranks translation equivalents of a target word according to similarity of their contexts to that of the target word. The second method ranks translation equivalents according to the ratio of associated words that suggest them. An experiment using the EDR bilingual dictionary together with Wall Street Journal and Nihon Keizai Shimbun corpora showed that the method using the ratio of associated words outperforms the method based on contextual similarity. Namely, in a quantitative evaluation using pseudo words, the maximum F-measure of the former method was 86%, while that of the latter method was 82%. The key feature of the method using the ratio of associated words is that it outputs selected translation equivalents together with representative associated words, enabling the translation equivalents to be validated.},
keywords={},
doi={10.1093/ietisy/e88-d.2.302},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - Adapting a Bilingual Dictionary to Domains
T2 - IEICE TRANSACTIONS on Information
SP - 302
EP - 312
AU - Hiroyuki KAJI
PY - 2005
DO - 10.1093/ietisy/e88-d.2.302
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2005
AB - Two methods using comparable corpora to select translation equivalents appropriate to a domain were devised and evaluated. The first method ranks translation equivalents of a target word according to similarity of their contexts to that of the target word. The second method ranks translation equivalents according to the ratio of associated words that suggest them. An experiment using the EDR bilingual dictionary together with Wall Street Journal and Nihon Keizai Shimbun corpora showed that the method using the ratio of associated words outperforms the method based on contextual similarity. Namely, in a quantitative evaluation using pseudo words, the maximum F-measure of the former method was 86%, while that of the latter method was 82%. The key feature of the method using the ratio of associated words is that it outputs selected translation equivalents together with representative associated words, enabling the translation equivalents to be validated.
ER -