Related papers: Por Qu\'e N\~ao Utiliser Alla Spr{\aa}k? Mixed Tra…
Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient…
In cross-lingual transfer, NLP models over one or more source languages are applied to a low-resource target language. While most prior work has used a single source model or a few carefully selected models, here we consider a `massive'…
Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT. Despite its growing popularity, little to no attention has been paid to standardizing and analyzing the…
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks. However, fine tuning such models requires a large number of training examples for each target task.…
Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in…
Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen…
Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…
Massively multilingual transformers pretrained with language modeling objectives (e.g., mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross-lingual transfer in NLP, offering unmatched transfer performance.…
Few-shot natural language processing (NLP) refers to NLP tasks that are accompanied with merely a handful of labeled examples. This is a real-world challenge that an AI system must learn to handle. Usually we rely on collecting more…
Although the advancements of pre-trained Large Language Models have significantly accelerated recent progress in NLP, their ever-increasing size poses significant challenges for conventional fine-tuning, especially in memory-intensive…
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…
Transfer learning between different language pairs has shown its effectiveness for Neural Machine Translation (NMT) in low-resource scenario. However, existing transfer methods involving a common target language are far from success in the…
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We…
Aspect-based sentiment analysis (ABSA) has received substantial attention in English, yet challenges remain for low-resource languages due to the scarcity of labelled data. Current cross-lingual ABSA approaches often rely on external…
We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the…
Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in languages with more sufficient training resources to generalize to other low-resource languages. Earlier efforts on this task use parallel…
Intermediate task fine-tuning has been shown to culminate in large transfer gains across many NLP tasks. With an abundance of candidate datasets as well as pre-trained language models, it has become infeasible to run the cross-product of…
While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be…