![]() ![]() ![]() We observe with only semantic constraints in the DA, the results are comparable with the scores obtained considering syntactic constraints, and is favourable for low-resourced languages that lacks linguistic toolsupport. This technique was experimented with low resource Sinhala-Englishlanguage pair. During augmentation,we consider both syntactic and semantic properties of the words to guarantee fluency in thesynthetic sentences. However, existing DA techniques have addressed only one of these OOV types and limit to considering eithersyntactic constraints or semantic constraints.We present a word and phrase replacement-based DA technique that consider both types ofOOV, by augmenting (1) rare words in the existing parallel corpus, and (2) new words froma bilingual dictionary. To alleviate this, word or phrase-based Data Augmentation (DA) techniques have been used. OOVrefers to words with a low occurrence in thetraining data, or to those that are absent fromthe training data. Out-of-Vocabulary (OOV) is a problem forNeural Machine Translation (NMT). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
December 2022
Categories |