Termhood-based Comparability Metrics of Comparable Corpus in Special Domain
This work addresses the scarcity of cross-language resources in special domains by improving comparability metrics for tasks like bilingual terminology extraction, though it is incremental as it builds on existing metrics approaches.
The paper tackles the problem of measuring comparability in specialized-domain comparable corpora for bilingual terminology extraction by proposing a termhood-based metrics method, which outperforms traditional frequency-based metrics in experiments.
Cross-Language Information Retrieval (CLIR) and machine translation (MT) resources, such as dictionaries and parallel corpora, are scarce and hard to come by for special domains. Besides, these resources are just limited to a few languages, such as English, French, and Spanish and so on. So, obtaining comparable corpora automatically for such domains could be an answer to this problem effectively. Comparable corpora, that the subcorpora are not translations of each other, can be easily obtained from web. Therefore, building and using comparable corpora is often a more feasible option in multilingual information processing. Comparability metrics is one of key issues in the field of building and using comparable corpus. Currently, there is no widely accepted definition or metrics method of corpus comparability. In fact, Different definitions or metrics methods of comparability might be given to suit various tasks about natural language processing. A new comparability, namely, termhood-based metrics, oriented to the task of bilingual terminology extraction, is proposed in this paper. In this method, words are ranked by termhood not frequency, and then the cosine similarities, calculated based on the ranking lists of word termhood, is used as comparability. Experiments results show that termhood-based metrics performs better than traditional frequency-based metrics.