How Should Markup Tags Be Translated?
The ability of machine translation (MT) models to correctly place markup is crucial to generating high-quality translations of formatted input. This paper compares two commonly used methods of representing markup tags and tests the ability of MT models to learn tag placement via training data augmentation. We study the interactions of tag representation, data augmentation size, tag complexity, and language pair to show the drawbacks and benefits of each method. We construct and release new test sets containing tagged data for three language pairs of varying difficulty.
Code (1)
Tasks
Data AugmentationMachine TranslationTAGTranslationSimilar Papers 제목 키워드 기반
TransIns: Document Translation with Markup Reinsertion
For many use cases, it is required that MT does not just translate raw text, but complex formatted documents (e.g. websites, slides, spreadsheets) and the result of the translation should reflect the formatting. This is …
Document TranslationNMTTranslationTreatment of Markup in Statistical Machine Translation
We present work on handling XML markup in Statistical Machine Translation (SMT). The methods we propose can be used to effectively preserve markup (for instance inline formatting or structure) and to place markup correct…
Machine TranslationTranslationAutomatic Bilingual Markup Transfer
We describe the task of bilingual markup transfer, which involves placing markup tags from a source sentence into a fixed target translation. This task arises in practice when a human translator generates the target tran…
Machine TranslationSentenceTranslationNICT’s Submission to the WAT 2022 Structured Document Translation Task
We present our submission to the structured document translation task organized by WAT 2022. In structured document translation, the key challenge is the handling of inline tags, which annotate text. Specifically, the te…
Document TranslationNMTSentenceTAG+1ICL Markup: Structuring In-Context Learning using Soft-Token Tags
Large pretrained language models (LLMs) can be rapidly adapted to a wide variety of tasks via a text-to-text approach, where the instruction and input are fed to the model in natural language. Combined with in-context le…
In-Context LearningIntent DetectionMeta-Learningparameter-efficient fine-tuning+2