Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation
We demonstrate a new approach to Neural Machine Translation (NMT) for low-resource languages using a ubiquitous linguistic resource, Interlinear Glossed Text (IGT). IGT represents a non-English sentence as a sequence of English lemmas and morpheme labels. As such, it can serve as a pivot or interlingua for NMT. Our contribution is four-fold. Firstly, we pool IGT for 1,497 languages in ODIN (54,545 glosses) and 70,918 glosses in Arapaho and train a gloss-to-target NMT system from IGT to English, with a BLEU score of 25.94. We introduce a multilingual NMT model that tags all glossed text with gloss-source language tags and train a universal system with shared attention across 1,497 languages. Secondly, we use the IGT gloss-to-target translation as a key step in an English-Turkish MT system trained on only 865 lines from ODIN. Thirdly, we we present five metrics for evaluating extremely low-resource translation when BLEU is no longer sufficient and evaluate the Turkish low-resource system using BLEU and also using accuracy of matching nouns, verbs, agreement, tense, and spurious repetition, showing large improvements.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNMTSentenceTranslationSimilar Papers 제목 키워드 기반
Wav2Gloss: Generating Interlinear Glossed Text from Speech
Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of linguistic annotation that can support …
DiversityMassively Multilingual Joint Segmentation and Glossing
Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchm…
Multilingual eXtended WordNet Knowledge Base: Semantic Parsing and Translation of Glosses
This paper presents a method to create WordNet-like lexical resources for different languages. Instead of directly translating glosses from one language to another, we perform first semantic parsing of WordNet glosses an…
Machine TranslationSemantic ParsingTranslationCWoMP: Morpheme Representation Learning for Interlinear Glossing
Interlinear glossed text (IGT) is a standard notation for language documentation which is linguistically rich but laborious to produce manually. Recent automated IGT methods treat glosses as character sequences, neglecti…
Representation LearningGrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning
We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations fo…
In-Context LearningMachine TranslationSentenceTranslation