Knowledge Based Template Machine Translation In Low-Resource Setting
Incorporating tagging into neural machine translation (NMT) systems has shown promising results in helping translate rare words such as named entities (NE). However, translating NE in low-resource setting remains a challenge. In this work, we investigate the effect of using tags and NE hypernyms from knowledge graphs (KGs) in parallel corpus in different level of resource conditions. We find the tag-and-copy mechanism (tag the NEs in the source sentence and copy them to the target sentence) improves translation in high-resource settings only. Introducing copying also results in polarizing effects in translating different parts-of-speech (POS). Interestingly, we find that copy accuracy for hypernyms is consistently higher than that of entities. As a way of avoiding "hard" copying and utilizing hypernym in bootstrapping rare entities, we introduced a "soft" tagging mechanism and found consistent improvement in high and low-resource setting.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsMachine TranslationNMTPOSSentenceTAGTranslationSimilar Papers 제목 키워드 기반
Knowledge Based Template Machine Translation In Low-Resource Setting
Incorporating tagging into neural machine translation (NMT) systems has shown promising results in helping translate rare words such as named entities (NE). However, translating NE in low-resource setting remains a chall…
Knowledge GraphsMachine TranslationNMTPOS+3POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation
Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machin…
Sign Language TranslationMachine TranslationThe Best Templates Match Technique For Example Based Machine Translation
It has been proved that large scale realistic Knowledge Based Machine Translation applications require acquisition of huge knowledge about language and about the world. This knowledge is encoded in computational grammars…
Machine TranslationTranslationLanguage Graph Distillation for Low-Resource Machine Translation
Neural machine translation on low-resource language is challenging due to the lack of bilingual sentence pairs. Previous works usually solve the low-resource translation problem with knowledge transfer in a multilingual …
Knowledge DistillationMachine TranslationSentenceTransfer Learning+1Paraphrasing Out-of-Vocabulary Words with Word Embeddings and Semantic Lexicons for Low Resource Statistical Machine Translation
Out-of-vocabulary (OOV) word is a crucial problem in statistical machine translation (SMT) with low resources. OOV paraphrasing that augments the translation model for the OOV words by using the translation knowledge of …
Machine TranslationTranslationWord Embeddings