Related papers: Exploring Methods for Building Dialects-Mandarin C…

Chinese text processing systems are using Double Byte Coding , while almost all existing Sanskrit Based Indian Languages have been using Single Byte coding for text processing. Through observation, Chinese Information Processing Technique…

Producing high-quality code across multiple programming languages is increasingly important as today's software systems are built on heterogeneous stacks. Large language models (LLMs) have advanced the state of automated programming, yet…

Previous cross-lingual transfer methods are restricted to orthographic representation learning via textual scripts. This limitation hampers cross-lingual transfer and is biased towards languages sharing similar well-known scripts. To…

Multilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix when conversing with…

While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing…

Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (\"U-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan…

Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…

Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data contains several challenges, especially due to grammatical…

Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-layer dual-decoder…

Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several works have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not…

Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social…

Standard-to-dialect machine translation remains challenging due to a persistent dialect gap in large language models and evaluation distortions inherent in n-gram metrics, which favor source copying over authentic dialect translation. In…

The surge in global migration patterns underscores the imperative of integrating migrants seamlessly into host communities, necessitating inclusive and trustworthy public services. Despite the Nordic countries' robust public sector…

Machine translation (MT) in the medical domain plays a pivotal role in enhancing healthcare quality and disseminating medical knowledge. Despite advancements in English-Thai MT technology, common MT approaches often underperform in the…

Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine…

Large Language Models (LLMs) excel at generating fluent text but struggle to enforce external constraints because they generate tokens sequentially without explicit control mechanisms. GenCP addresses this limitation by combining LLM…

An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and…

Speech large language models (SLLMs) built on speech encoders, adapters, and LLMs demonstrate remarkable multitask understanding performance in high-resource languages such as English and Chinese. However, their effectiveness substantially…

Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…

Evaluating the performance of Code Language Models (CLMs) for software engineering tasks, especially in multilingual and low-resource programming language settings, poses significant challenges. These challenges are primarily due to the…