Related papers: Zero-shot Neural Transfer for Cross-lingual Entity…

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast array of these resources, most…

The Zero-Shot Learning (ZSL) task pertains to the identification of entities or relations in texts that were not seen during training. ZSL has emerged as a critical research area due to the scarcity of labeled data in specific domains, and…

Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability. Previous methods largely focus on the candidate retrieval stage and ignore the essential candidate ranking stage,…

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some languages, but it is…

Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…

Entity linking (EL) is the computational process of connecting textual mentions to corresponding entities. Like many areas of natural language processing, the EL field has greatly benefited from deep learning, leading to significant…

Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word…

In this paper, we introduce a zero-shot Voice Transfer (VT) module that can be seamlessly integrated into a multi-lingual Text-to-speech (TTS) system to transfer an individual's voice across languages. Our proposed VT module comprises a…

Recent advances have enabled Large Language Models (LLMs) to tackle reasoning tasks by generating chain-of-thought (CoT) rationales, yet these gains have largely applied to high-resource languages, leaving low-resource languages behind. In…

Multilingual language models have pushed state-of-the-art in cross-lingual NLP transfer. The majority of zero-shot cross-lingual transfer, however, use one and the same massively multilingual transformer (e.g., mBERT or XLM-R) to transfer…

The cross-lingual transfer is a promising technique to solve tasks in less-resourced languages. In this empirical study, we compare two fine-tuning approaches combined with zero-shot and full-shot learning approaches for large language…

To better tackle the named entity recognition (NER) problem on languages with little/no labeled data, cross-lingual NER must effectively leverage knowledge learned from source languages with rich labeled data. Previous works on…

Providing better language tools for low-resource and endangered languages is imperative for equitable growth. Recent progress with massively multilingual pretrained models has proven surprisingly effective at performing zero-shot transfer…

End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the…

Predicting user intent and detecting the corresponding slots from text are two key problems in Natural Language Understanding (NLU). In the context of zero-shot learning, this task is typically approached by either using representations…

Transferring representations from large supervised tasks to downstream tasks has shown promising results in AI fields such as Computer Vision and Natural Language Processing (NLP). In parallel, the recent progress in Machine Translation…

We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-language data. We experiment with two pretrained multilingual…

A significant shortcoming of current state-of-the-art (SOTA) named-entity recognition (NER) systems is their lack of generalization to unseen domains, which poses a major problem since obtaining labeled data for NER in a new domain is…

Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks such as translation and multilingual word sense disambiguation (WSD). However, they often struggle at disambiguating…

Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in…