Related papers: IndoRobusta: Towards Robustness Against Diverse Co…

Code-mixing is a phenomenon which arises mainly in multilingual societies. Multilingual people, who are well versed in their native languages and also English speakers, tend to code-mix using English-based phonetic typing and the insertion…

The success of several architectures to learn semantic representations from unannotated text and the availability of these kind of texts in online multilingual resources such as Wikipedia has facilitated the massive and automatic creation…

With the extensive use of vision-language models in various downstream tasks, evaluating their robustness is crucial. In this paper, we propose a benchmark for assessing the robustness of vision-language models. We believe that a robust…

Existing research predominantly focuses on developing powerful language learning models (LLMs) for mathematical reasoning within monolingual languages, with few explorations in preserving efficacy in a multilingual context. To bridge this…

Cross-lingual transfer is essential for building NLP systems for low-resource African languages, but practitioners lack reliable methods for selecting source languages. We systematically evaluate five embedding similarity metrics across 816…

While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development. Existing tokenizers often exhibit high…

Social media platforms such as Twitter and Facebook are becoming popular in multilingual societies. This trend induces portmanteau of South Asian languages with English. The blend of multiple languages as code-mixed data has recently become…

Code-Mixing is a phenomenon of mixing two or more languages in a speech event and is prevalent in multilingual societies. Given the low-resource nature of Code-Mixing, machine generation of code-mixed text is a prevalent approach for data…

This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, on three code-switched corpora. We found that self-supervised…

Translation of code-mixed texts to formal English allow a wider audience to understand these code-mixed languages, and facilitate downstream analysis applications such as sentiment analysis. In this work, we look at translating Singlish,…

Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally desirable, it becomes a critical failure when…

Large Language Models (LLMs) excel in English, but their performance degrades significantly on low-resource languages (LRLs) due to English-centric training. While methods like LangBridge align LLMs with multilingual encoders such as the…

A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy is usually used to…

Development of language proficiency models for non-native learners has been an active area of interest in NLP research for the past few years. Although language proficiency is multidimensional in nature, existing research typically…

The emergence of unsupervised word embeddings, pre-trained on very large monolingual text corpora, is at the core of the ongoing neural revolution in Natural Language Processing (NLP). Initially introduced for English, such pre-trained word…

Neural network has shown promising performance on coreference resolution systems that uses mention pair method. With deep neural network, it can learn hidden and deep relations between two mentions. However, there is no work on coreference…

Large language models (LLMs) increasingly assist software engineering tasks that require reasoning over long code contexts, yet their robustness under varying input conditions remains unclear. We conduct a systematic study of long-context…

Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…

Making use of off-the-shelf resources of resource-rich languages to transfer knowledge for low-resource languages raises much attention recently. The requirements of enabling the model to reach the reliable performance lack well guided,…