Related papers: Unsung Challenges of Building and Deploying Langua…

While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource…

The challenge of language grounding is to fully understand natural language by grounding language in real-world referents. While AI techniques are available, the widespread adoption and effectiveness of such technologies for human-robot…

Advancements in natural language generation (NLG) and large language models (LLMs) have led to proficient text generation in various tasks. However, integrating intricate constraints into neural text generation, due to LLMs' opacity,…

This paper presents an overview of a program designed to address the growing need for developing freely available speech resources for under-represented languages. At present we have released 38 datasets for building text-to-speech and…

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP…

Tokenization plays a pivotal role in multilingual NLP. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those…

Language models (LM or LLM) are increasingly deployed in the field of artificial intelligence (AI) and its applications, but the question arises as to whether they can be a common resource managed and maintained by a community of users.…

Automatic spoken language identification (LID) is a very important research field in the era of multilingual voice-command-based human-computer interaction (HCI). A front-end LID module helps to improve the performance of many speech-based…

Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable…

The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which…

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…

Existing research in measuring and mitigating gender bias predominantly centers on English, overlooking the intricate challenges posed by non-English languages and the Global South. This paper presents the first comprehensive study delving…

Multilingual large language models (LLMs) often demonstrate a performance gap between English and non-English languages, particularly in low-resource settings. Aligning these models to low-resource languages is essential yet challenging due…

In this survey, we systematically analyze techniques used to adapt large multimodal models (LMMs) for low-resource (LR) languages, examining approaches ranging from visual enhancement and data creation to cross-modal transfer and fusion…

Over the past few years, improving LLM code generation capabilities has been a key focus in NLP research. Despite Bengali having 242 million native speakers worldwide, it receives little attention when it comes to training LLMs. More…

It is well known that AI-based language technology -- large language models, machine translation systems, multilingual dictionaries, and corpora -- is currently limited to 2 to 3 percent of the world's most widely spoken and/or financially…

The advent of Large Language Models has revolutionized information retrieval, ushering in a new era of expansive knowledge accessibility. While these models excel in providing open-world knowledge, effectively extracting answers in diverse…

Developing Information Retrieval (IR) tools and techniques in African languages suffers from the dual problems of a lack of algorithms and very small test data collections. This affects the creation of practical IR systems and limits the…

Using large language models, this paper presents techniques to improve extremely low-resourced indigenous language translations. Our approaches are grounded in the use of (1) the presence of a datastore consisting of a limited number of…