相关论文: UXLA: A Robust Unsupervised Data Augmentation Fram…

Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…

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…

Recently, although pre-trained language models have achieved great success on multilingual NLP (Natural Language Processing) tasks, the lack of training data on many tasks in low-resource languages still limits their performance. One…

While natural language processing systems often focus on a single language, multilingual transfer learning has the potential to improve performance, especially for low-resource languages. We introduce XLDA, cross-lingual data augmentation,…

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…

Natural language understanding (NLU) is the task of semantic decoding of human languages by machines. NLU models rely heavily on large training data to ensure good performance. However, substantial languages and domains have very few data…

Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages (HRLs) to low-resource languages (LRLs). However, the…

We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP. Our approach is based on prompting off-the-shelf…

Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled auxiliary set to…

The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety of methods aiming to close the gap to high-resource…

The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource…

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…

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…

Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks.…

State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used…

In zero-shot cross-lingual transfer, a supervised NLP task trained on a corpus in one language is directly applicable to another language without any additional training. A source of cross-lingual transfer can be as straightforward as…

This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the…

Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…

Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We…

Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before…