Related papers: A Novel Multi-Task Learning Approach for Context-S…

Code-mixing, the blending of linguistic elements from distinct languages to form meaningful sentences, is common in multilingual settings, yielding hybrid languages like Hinglish and Minglish. Marathi, India's third most spoken language,…

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We…

How to usefully encode compositional task structure has long been a core challenge in AI. Recent work in chain of thought prompting has shown that for very large neural language models (LMs), explicitly demonstrating the inferential steps…

We address the challenges and opportunities in the development of knowledge systems for Sanskrit, with a focus on question answering. By proposing a framework for the automated construction of knowledge graphs, introducing annotation tools…

Language models (LMs) are capable of acquiring elements of human-like syntactic knowledge. Targeted syntactic evaluation tests have been employed to measure how well they form generalizations about syntactic phenomena in high-resource…

Sanskrit is a classical language with about 30 million extant manuscripts fit for digitisation, available in written, printed or scannedimage forms. However, it is still considered to be a low-resource language when it comes to available…

The language diversity in India's education sector poses a significant challenge, hindering inclusivity. Despite the democratization of knowledge through online educational content, the dominance of English, as the internet's lingua franca,…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

Finding the semantically accurate answer is one of the key challenges in advanced searching. In contrast to keyword-based searching, the meaning of a question or query is important here and answers are ranked according to relevance. It is…

The rise of neural networks, and particularly recurrent neural networks, has produced significant advances in part-of-speech tagging accuracy. One characteristic common among these models is the presence of rich initial word encodings.…

Sandhi means to join two or more words to coin new word. Sandhi literally means `putting together' or combining (of sounds), It denotes all combinatory sound-changes effected (spontaneously) for ease of pronunciation. Sandhi-vicheda…

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…

Many of the existing approaches for program comprehension rely on the linguistic information found in source code, such as identifier names and comments. Semantic clustering is one such technique for modularization of the system that relies…

Code-switching is a commonly observed communicative phenomenon denoting a shift from one language to another within the same speech exchange. The analysis of code-switched data often becomes an assiduous task, owing to the limited…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Topic modeling is a key method in text analysis, but existing approaches fail to efficiently scale to large datasets or are limited by assuming one topic per document. Overcoming these limitations, we introduce Semantic Component Analysis…

Semantic sparsity is a common challenge in structured visual classification problems; when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic…

We propose SETI (Systematicity Evaluation of Textual Inference), a novel and comprehensive benchmark designed for evaluating pre-trained language models (PLMs) for their systematicity capabilities in the domain of textual inference.…

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…

Knowledge Tracing (KT) aims to determine whether students will respond correctly to the next question, which is a crucial task in intelligent tutoring systems (ITS). In educational KT scenarios, transductive ID-based methods often face…