Data Augmentation for Machine Translation via Dependency Subtree Swapping
We present a generic framework for data augmentation via dependency subtree swapping that is applicable to machine translation. We extract corresponding subtrees from the dependency parse trees of the source and target sentences and swap these across bisentences to create augmented samples. We perform thorough filtering based on graphbased similarities of the dependency trees and additional heuristics to ensure that extracted subtrees correspond to the same meaning. We conduct resource-constrained experiments on 4 language pairs in both directions using the IWSLT text translation datasets and the Hunglish2 corpus. The results demonstrate consistent improvements in BLEU score over our baseline models in 3 out of 4 language pairs. Our code is available on GitHub.
Code (2)
Tasks
Data AugmentationMachine TranslationTranslationSimilar Papers 제목 키워드 기반
TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping
Data augmentation methods for neural machine translation are particularly useful when limited amount of training data is available, which is often the case when dealing with low-resource languages. We introduce a novel a…
Data AugmentationMachine TranslationTranslationData Augmentation via Subtree Swapping for Dependency Parsing of Low-Resource Languages
The lack of annotated data is a big issue for building reliable NLP systems for most of the world{'}s languages. But this problem can be alleviated by automatic data generation. In this paper, we present a new data augme…
Data AugmentationDependency ParsingDependency Parsing as MRC-based Span-Span Prediction
Higher-order methods for dependency parsing can partially but not fully address the issue that edges in dependency trees should be constructed at the text span/subtree level rather than word level. In this paper, we prop…
Dependency ParsingMachine Reading ComprehensionPredictionReading ComprehensionDeveloping neural machine translation models for Hungarian-English
I train models for the task of neural machine translation for English-Hungarian and Hungarian-English, using the Hunglish2 corpus. The main contribution of this work is evaluating different data augmentation methods duri…
Data AugmentationDependency ParsingMachine TranslationNMT+1Large-scale Word Alignment Using Soft Dependency Cohesion Constraints
Dependency cohesion refers to the observation that phrases dominated by disjoint dependency subtrees in the source language generally do not overlap in the target language. It has been verified to be a useful constraint …
Machine TranslationTranslationWord Alignment