Related papers: Chandomitra: Towards Generating Structured Sanskri…
In this paper, we explore the utility of translationese as synthetic data created using machine translation for pre-training language models (LMs) for low-resource languages (LRLs). Our simple methodology consists of translating large…
Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry. Much prior work on poetry generation uses manually defined constraints which are…
The primary focus of this thesis is to make Sanskrit manuscripts more accessible to the end-users through natural language technologies. The morphological richness, compounding, free word orderliness, and low-resource nature of Sanskrit…
The use of language models for generating lyrics and poetry has received an increased interest in the last few years. They pose a unique challenge relative to standard natural language problems, as their ultimate purpose is reative, notions…
Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate…
Poetry generation, and creative language generation in general, usually suffers from the lack of large training data. In this paper, we present a novel framework to generate sonnets that does not require training on poems. We design a…
The advancements in the Large Language Model (LLM) have helped in solving several problems related to language processing. Most of the researches have focused on the English language only, because of its popularity and abundance on the…
Large Language Models (LLMs) are now capable of generating text that closely resembles human writing, making them powerful tools for content creation, but this growing ability has also made it harder to tell whether a piece of text was…
The long-range dependencies among the tokens, which originate from hierarchical structures, are a defining hallmark of human language. However, whether similar dependencies exist within the sequential vocalization of non-human animals…
Generating poetry has become a popular application of LLMs, perhaps especially of OpenAI's widely-used chatbot ChatGPT. What kind of poet is ChatGPT? Does ChatGPT have its own poetic style? Can it successfully produce poems in different…
Effective communication, specifically through documentation, is the beating heart of collaboration among contributors in software development. Recent advancements in language models (LMs) have enabled the introduction of a new type of actor…
Morphologically rich languages are notoriously challenging to process for downstream NLP applications. This paper presents a new pretrained language model, ByT5-Sanskrit, designed for NLP applications involving the morphologically rich…
In recent years, large language models (LLMs) have emerged as powerful tools with potential applications in various fields, including software engineering. Within the scope of this research, we evaluate five different state-of-the-art LLMs…
Sanskrit, one of humanity's most ancient languages, has a vast collection of books and manuscripts on diverse topics that have been accumulated over millennia. However, its digital content (audio and text), which is vital for the training…
Tokens are the basic units of Large Language Models (LLMs). LLMs rely on tokenizers to segment text into these tokens, and tokenization is the primary determinant of computational and inference cost. Sanskrit, one of the oldest languages,…
Recently, there has been a surge in interest in NLP driven by ChatGPT. ChatGPT, a transformer-based generative language model of substantial scale, exhibits versatility in performing various tasks based on natural language. Nevertheless,…
It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn…
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…
Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…
General large language models (LLMs) such as ChatGPT have shown remarkable success, but it has also raised concerns among people about the misuse of AI-generated texts. Therefore, an important question is how to detect whether the texts are…