A little perturbation makes a difference: Treebank augmentation by perturbation improves transfer parsing
We present an approach for cross-lingual transfer of dependency parser so that the parser trained on a single source language can more effectively cater to diverse target languages. In this work, we show that the cross-lingual performance of the parsers can be enhanced by over-generating the source language treebank. For this, the source language treebank is augmented with its perturbed version in which controlled perturbation is introduced in the parse trees by stochastically reordering the positions of the dependents with respect to their heads while keeping the structure of the parse trees unchanged. This enables the parser to capture diverse syntactic patterns in addition to those that are found in the source language. The resulting parser is found to more effectively parse target languages with different syntactic structures. With English as the source language, our system shows an average improvement of 6.7% and 7.7% in terms of UAS and LAS over 29 target languages compared to the baseline single source parser trained using unperturbed source language treebank. This also results in significant improvement over the transfer parser proposed by (CITATION) that involves an “order-free” parser algorithm.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Lingual TransferSimilar Papers 제목 키워드 기반
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
Edge perturbation is a basic method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i.e., graph data augmentation and attack. Su…
Data AugmentationGraph Neural NetworkAchieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to par…
Data Augmentationtext-classificationText ClassificationParser Training with Heterogeneous Treebanks
How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question. We start by investigating previously suggested, but little evaluated, strategies for exploiting …
Open-Ended Question AnsweringCross-lingual Inflection as a Data Augmentation Method for Parsing
We propose a morphology-based method for low-resource (LR) dependency parsing. We train a morphological inflector for target LR languages, and apply it to related rich-resource (RR) treebanks to create cross-lingual (x-i…
Data AugmentationDependency ParsingA systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages
Parsers are available for only a handful of the world's languages, since they require lots of training data. How far can we get with just a small amount of training data? We systematically compare a set of simple strateg…
Data AugmentationDependency ParsingTransliteration