Related papers: Harnessing Linguistic Dissimilarity for Language G…

Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected…

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language…

Multilingual information retrieval has emerged as powerful tools for expanding knowledge sharing across languages. On the other hand, resources on high quality knowledge base are often scarce and in limited languages, therefore an effective…

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…

Linguistic typology aims to capture structural and semantic variation across the world's languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that…

Data abundance across different domains exhibits a long-tailed distribution: few domains have abundant data, while most face data scarcity. Our work focuses on a multilingual setting, where available data is heavily skewed towards…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candidate for this, as…

In this paper, we address the data scarcity problem in automatic data-driven glossing for low-resource languages by coordinating multiple sources of linguistic expertise. We supplement models with translations at both the token and sentence…

The central bottleneck for low-resource NLP is typically regarded to be the quantity of accessible data, overlooking the contribution of data quality. This is particularly seen in the development and evaluation of low-resource systems via…

Neural language models often struggle with low-resource languages due to the limited availability of training data, making tokens from these languages rare in the training set. This paper addresses a specific challenge during training: rare…

Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource languages. To further expand the range of languages these models can support, many works focus on continued pre-training of these models.…

Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…

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…

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…

Pretrained multilingual encoders enable zero-shot cross-lingual transfer, but often produce unreliable models that exhibit high performance variance on the target language. We postulate that this high variance results from zero-shot…

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…

Pretrained multilingual language models have become a common tool in transferring NLP capabilities to low-resource languages, often with adaptations. In this work, we study the performance, extensibility, and interaction of two such…

Benefiting from transformer-based pre-trained language models, neural ranking models have made significant progress. More recently, the advent of multilingual pre-trained language models provides great support for designing neural…