Related papers: Leveraging Large Language Models for Code-Mixed Da…
Accurate sentiment analysis of texts is crucial for a variety of applications, such as understanding customer feedback, monitoring market trends, and detecting public sentiment. However, manually annotating large sentiment corpora for…
While many languages possess processes of joining two or more words to create compound words, previous studies have been typically limited only to languages with excessively productive compound formation (e.g., German, Dutch) and there is…
Large language models are increasingly trained on corpora containing both natural language and non-linguistic data like source code. Aside from aiding programming-related tasks, anecdotal evidence suggests that including code in pretraining…
Methods such as chain-of-thought prompting and self-consistency have pushed the frontier of language model reasoning performance with no additional training. To further improve performance, we propose a prompt ensembling method for large…
Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…
Problems involving code-mixed language are often plagued by a lack of resources and an absence of materials to perform sophisticated transfer learning with. In this paper we describe our submission to the Sentimix Hindi-English task…
Knowledge Components (KCs) are foundational to adaptive learning systems, but their manual identification by domain experts is a significant bottleneck. While Large Language Models (LLMs) offer a promising avenue for automating this…
The increasing use of social media sites in countries like India has given rise to large volumes of code-mixed data. Sentiment analysis of this data can provide integral insights into people's perspectives and opinions. Developing robust…
Fact-checking for health-related content is challenging due to the limited availability of annotated training data. In this study, we propose a synthetic data generation pipeline that leverages large language models (LLMs) to augment…
Large language models (LLMs) have shown remarkable potential for problem solving, with open source models achieving increasingly impressive performance on benchmarks measuring areas from logical reasoning to mathematical ability. Ensembling…
Models are increasing in size and complexity in the hunt for SOTA. But what if those 2\% increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight…
Large Language Models (LLMs) have achieved significant advancements, but the increasing complexity of tasks and higher performance demands highlight the need for continuous improvement. Some approaches utilize synthetic data generated by…
Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for…
Code-switching (CS) is still a critical challenge in Natural Language Processing (NLP), due to the limited availability of large-scale, diverse CS datasets for robust training and evaluation. Despite recent advances, the capabilities and…
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by…
This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-English (ZH-EN) language pairs. The task aims to advance…
Sentiment analysis (SA) has been a long-standing research area in natural language processing. It can offer rich insights into human sentiments and opinions and has thus seen considerable interest from both academia and industry. With the…
Ambiguous words are often found in modern digital communications. Lexical ambiguity challenges traditional Word Sense Disambiguation (WSD) methods, due to limited data. Consequently, the efficiency of translation, information retrieval, and…
State-of-the-art text-to-speech (TTS) systems realize high naturalness in monolingual environments, synthesizing speech with correct multilingual accents (especially for Indic languages) and context-relevant emotions still poses difficulty…
Large Language Models (LLMs) have shown remarkable capabilities, but their development has primarily focused on English and other high-resource languages, leaving many languages underserved. We present our latest Hindi-English bi-lingual…