TY - GEN
T1 - Plan optimization for creating bilingual dictionaries of low-resource languages
AU - Nasution, Arbi Haza
AU - Murakami, Yohei
AU - Ishida, Toru
N1 - Funding Information:
This research was partially supported by a Grant-in-Aid for Scientific Research (A) (17H00759, 2017-2020) and a Grant-in-Aid for Young Scientists (A) (17H04706, 2017-2020) from Japan Society for the Promotion of Science (JSPS). The first author was supported by Indonesia En-downment Fund for Education (LPDP).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/19
Y1 - 2017/12/19
N2 - The constraint-based approach has been proven useful for inducing bilingual lexicons for closely-related low-resource languages. When we want to create multiple bilingual dictionaries linking several languages, we need to consider manual creation by bilingual language experts if there are no available machine-readable dictionaries are available as input. To overcome the difficulty in planning the creation of bilingual dictionaries, the consideration of various methods and costs, plan optimization is essential. We adopt the Markov Decision Process (MDP) in formalizing plan optimization for creating bilingual dictionaries; the goal is to better predict the most feasible optimal plan with the least total cost before fully implementing the constraint-based bilingual dictionary induction framework. We define heuristics based on input language characteristics to devise a baseline plan for evaluating our MDP-based approach with total cost as an evaluation metric. The MDP-based proposal outperformed heuristic planning on total cost for all datasets examined.
AB - The constraint-based approach has been proven useful for inducing bilingual lexicons for closely-related low-resource languages. When we want to create multiple bilingual dictionaries linking several languages, we need to consider manual creation by bilingual language experts if there are no available machine-readable dictionaries are available as input. To overcome the difficulty in planning the creation of bilingual dictionaries, the consideration of various methods and costs, plan optimization is essential. We adopt the Markov Decision Process (MDP) in formalizing plan optimization for creating bilingual dictionaries; the goal is to better predict the most feasible optimal plan with the least total cost before fully implementing the constraint-based bilingual dictionary induction framework. We define heuristics based on input language characteristics to devise a baseline plan for evaluating our MDP-based approach with total cost as an evaluation metric. The MDP-based proposal outperformed heuristic planning on total cost for all datasets examined.
KW - Closely-related Languages
KW - Low-resource Languages
KW - Markov Decision Process
KW - Pivot-based Bilingual Dictionary Induction
KW - Plan Optimization
UR - http://www.scopus.com/inward/record.url?scp=85047568764&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047568764&partnerID=8YFLogxK
U2 - 10.1109/Culture.and.Computing.2017.21
DO - 10.1109/Culture.and.Computing.2017.21
M3 - Conference contribution
AN - SCOPUS:85047568764
T3 - Proceedings - 2017 International Conference on Culture and Computing, Culture and Computing 2017
SP - 35
EP - 41
BT - Proceedings - 2017 International Conference on Culture and Computing, Culture and Computing 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Conference on Culture and Computing, Culture and Computing 2017
Y2 - 10 September 2017 through 12 September 2017
ER -