Related papers: Low-Resource Syntactic Transfer with Unsupervised …
We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available. The method makes use of three steps: 1) a method for deriving…
Cross-lingual transfer is an effective way to build syntactic analysis tools in low-resource languages. However, transfer is difficult when transferring to typologically distant languages, especially when neither annotated target data nor…
Treebank translation is a promising method for cross-lingual transfer of syntactic dependency knowledge. The basic idea is to map dependency arcs from a source treebank to its target translation according to word alignments. This method,…
Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource…
Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we propose an effective…
Cross-lingual dependency parsing involves transferring syntactic knowledge from one language to another. It is a crucial component for inducing dependency parsers in low-resource scenarios where no training data for a language exists. Using…
We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is…
We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that…
Different languages might have different word orders. In this paper, we investigate cross-lingual transfer and posit that an order-agnostic model will perform better when transferring to distant foreign languages. To test our hypothesis, we…
Prior work on cross-lingual dependency parsing often focuses on capturing the commonalities between source and target languages and overlooks the potential of leveraging linguistic properties of the languages to facilitate the transfer. In…
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 strategies for improving…
We release Galactic Dependencies 1.0---a large set of synthetic languages not found on Earth, but annotated in Universal Dependencies format. This new resource aims to provide training and development data for NLP methods that aim to adapt…
Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource settings remains poorly understood. We evaluate four parsers -- the Biaffine…
This study examines the cross-linguistic effectiveness of transfer learning for low-resource machine translation by fine-tuning models initially trained on typologically similar high-resource languages, using limited data from the target…
Singlish can be interesting to the ACL community both linguistically as a major creole based on English, and computationally for information extraction and sentiment analysis of regional social media. We investigate dependency parsing of…
Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language…
Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the…
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75…
Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom…
We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous…