Related papers: Sample-Efficient Language Model for Hinglish Conve…
Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non English languages are less explored due to limited benchmarks and training data. To bridge this gap, we introduce the Indic QA Benchmark, a…
Current Text-to-Speech models pose a multilingual challenge, where most of the models traditionally focus on English and European languages, thereby hurting the potential to provide access to information to many more people. To address this…
Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages. Despite the promising performance of sentence-level and context-aware neural machine translation models, there still remain…
Many users communicate with chatbots and AI assistants in order to help them with various tasks. A key component of the assistant is the ability to understand and answer a user's natural language questions for question-answering (QA).…
Certain pairs of languages suffer from lack of a parallel corpus which is large in size and diverse in domain. One of the ways this is overcome is via use of a pivot language. In this paper we use Hindi as a pivot language to translate…
Spoken Language Models (SLMs) aim to learn linguistic competence directly from speech using discrete units, widening access to Natural Language Processing (NLP) technologies for languages with limited written resources. However, progress…
Large language models have transformed AI-assisted software engineering, but current research remains biased toward high-resource languages such as Python, with weaker performance in languages like Rust and OCaml. Since real-world systems…
Natural language processing (NLP) techniques have become mainstream in the recent decade. Most of these advances are attributed to the processing of a single language. More recently, with the extensive growth of social media platforms focus…
The dominance of large multilingual foundation models has widened linguistic inequalities in Natural Language Processing (NLP), often leaving low-resource languages underrepresented. This paper introduces LilMoo, a 0.6-billion-parameter…
Generative AI and large language models hold great promise in enhancing programming education by generating individualized feedback and hints for learners. Recent works have primarily focused on improving the quality of generated feedback…
End-to-end (E2E) models have been explored for large speech corpora and have been found to match or outperform traditional pipeline-based systems in some languages. However, most prior work on end-to-end models use speech corpora exceeding…
Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…
Cross-lingual conversational speech summarization is an important problem, but suffers from a dearth of resources. While transcriptions exist for a number of languages, translated conversational speech is rare and datasets containing…
We describe the latest improvements to the IBM English conversational telephone speech recognition system. Some of the techniques that were found beneficial are: maxout networks with annealed dropout rates; networks with a very large number…
The main limiting factor in the development of robust multilingual dialogue evaluation metrics is the lack of multilingual data and the limited availability of open sourced multilingual dialogue systems. In this work, we propose a…
Work on retrieval-based chatbots, like most sequence pair matching tasks, can be divided into Cross-encoders that perform word matching over the pair, and Bi-encoders that encode the pair separately. The latter has better performance,…
Achieving high-performing language models which include medium- and lower-resource languages remains a challenge. Massively multilingual models still underperform compared to language-specific adaptations, especially at smaller model…
Spoken English proficiency is a powerful driver of economic mobility for low-income Indian youth, yet opportunities for spoken practice remain scarce in schools. We investigate the deployment of a voice-based chatbot for English…
Question-answering (QA) that comes naturally to humans is a critical component in seamless human-computer interaction. It has emerged as one of the most convenient and natural methods to interact with the web and is especially desirable in…
Hybrid intelligence aims to enhance decision-making, problem-solving, and overall system performance by combining the strengths of both, human cognitive abilities and artificial intelligence. With the rise of Large Language Models (LLM),…