Related papers: Detecting Languages Unintelligible to Multilingual…
Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. While there has been much work in evaluating these models for their performance on a variety of…
Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…
We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge…
The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to…
Multilingual pre-trained language models (MPLMs) not only can handle tasks in different languages but also exhibit surprising zero-shot cross-lingual transferability. However, MPLMs usually are not able to achieve comparable supervised…
English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…
Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the…
Despite their success, large pre-trained multilingual models have not completely alleviated the need for labeled data, which is cumbersome to collect for all target languages. Zero-shot cross-lingual transfer is emerging as a practical…
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning…
In today's global digital landscape, misinformation transcends linguistic boundaries, posing a significant challenge for moderation systems. Most approaches to misinformation detection are monolingual, focused on high-resource languages,…
Speech processing systems currently do not support the vast majority of languages, in part due to the lack of data in low-resource languages. Cross-lingual transfer offers a compelling way to help bridge this digital divide by incorporating…
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…
Despite cross-lingual generalization demonstrated by pre-trained multilingual models, the translate-train paradigm of transferring English datasets across multiple languages remains to be a key mechanism for training task-specific…
Multilingual pretrained language models (such as multilingual BERT) have achieved impressive results for cross-lingual transfer. However, due to the constant model capacity, multilingual pre-training usually lags behind the monolingual…
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…
Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…
Substantial improvements have been made in machine reading comprehension, where the machine answers questions based on a given context. Current state-of-the-art models even surpass human performance on several benchmarks. However, their…
Misinformation spread over social media has become an undeniable infodemic. However, not all spreading claims are made equal. If propagated, some claims can be destructive, not only on the individual level, but to organizations and even…
Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…