A Method for Reinforcing Noun Countability Prediction
Summary :
This paper proposes a method for reinforcing noun countability prediction, which plays a crucial role in demarcating correct determiners in machine translation and error detection. The proposed method reinforces countability prediction by introducing a novel heuristics called one countability per discourse. It claims that when a noun appears more than once in a discourse, all instances will share identical countability. The basic idea of the proposed method is that mispredictions can be corrected by efficiently using one countability per discourse heuristics. Experiments show that the proposed method successfully reinforces countability prediction and outperforms other methods used for comparison. In addition to its performance, it has two advantages over earlier methods: (i) it is applicable to any countability prediction method, and (ii) it requires no human intervention to reinforce countability prediction.
- Publication
- IEICE TRANSACTIONS on Information Vol.E90-D No.12 pp.2077-2086
- Publication Date
- 2007/12/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e90-d.12.2077
- Type of Manuscript
- PAPER
- Category
- Natural Language Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Ryo NAGATA, Atsuo KAWAI, Koichiro MORIHIRO, Naoki ISU, "A Method for Reinforcing Noun Countability Prediction" in IEICE TRANSACTIONS on Information,
vol. E90-D, no. 12, pp. 2077-2086, December 2007, doi: 10.1093/ietisy/e90-d.12.2077.
Abstract: This paper proposes a method for reinforcing noun countability prediction, which plays a crucial role in demarcating correct determiners in machine translation and error detection. The proposed method reinforces countability prediction by introducing a novel heuristics called one countability per discourse. It claims that when a noun appears more than once in a discourse, all instances will share identical countability. The basic idea of the proposed method is that mispredictions can be corrected by efficiently using one countability per discourse heuristics. Experiments show that the proposed method successfully reinforces countability prediction and outperforms other methods used for comparison. In addition to its performance, it has two advantages over earlier methods: (i) it is applicable to any countability prediction method, and (ii) it requires no human intervention to reinforce countability prediction.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.12.2077/_p
Copy
@ARTICLE{e90-d_12_2077,
author={Ryo NAGATA, Atsuo KAWAI, Koichiro MORIHIRO, Naoki ISU, },
journal={IEICE TRANSACTIONS on Information},
title={A Method for Reinforcing Noun Countability Prediction},
year={2007},
volume={E90-D},
number={12},
pages={2077-2086},
abstract={This paper proposes a method for reinforcing noun countability prediction, which plays a crucial role in demarcating correct determiners in machine translation and error detection. The proposed method reinforces countability prediction by introducing a novel heuristics called one countability per discourse. It claims that when a noun appears more than once in a discourse, all instances will share identical countability. The basic idea of the proposed method is that mispredictions can be corrected by efficiently using one countability per discourse heuristics. Experiments show that the proposed method successfully reinforces countability prediction and outperforms other methods used for comparison. In addition to its performance, it has two advantages over earlier methods: (i) it is applicable to any countability prediction method, and (ii) it requires no human intervention to reinforce countability prediction.},
keywords={},
doi={10.1093/ietisy/e90-d.12.2077},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - A Method for Reinforcing Noun Countability Prediction
T2 - IEICE TRANSACTIONS on Information
SP - 2077
EP - 2086
AU - Ryo NAGATA
AU - Atsuo KAWAI
AU - Koichiro MORIHIRO
AU - Naoki ISU
PY - 2007
DO - 10.1093/ietisy/e90-d.12.2077
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2007
AB - This paper proposes a method for reinforcing noun countability prediction, which plays a crucial role in demarcating correct determiners in machine translation and error detection. The proposed method reinforces countability prediction by introducing a novel heuristics called one countability per discourse. It claims that when a noun appears more than once in a discourse, all instances will share identical countability. The basic idea of the proposed method is that mispredictions can be corrected by efficiently using one countability per discourse heuristics. Experiments show that the proposed method successfully reinforces countability prediction and outperforms other methods used for comparison. In addition to its performance, it has two advantages over earlier methods: (i) it is applicable to any countability prediction method, and (ii) it requires no human intervention to reinforce countability prediction.
ER -
English
