中文
相关论文

相关论文: Using n-aksaras to model Sanskrit and Sanskrit-adj…

200 篇论文

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,…

计算与语言 · 计算机科学 2026-01-13 Anshul Kumar

Automatic speech recognition (ASR) in Sanskrit is interesting, owing to the various linguistic peculiarities present in the language. The Sanskrit language is lexically productive, undergoes euphonic assimilation of phones at the word…

音频与语音处理 · 电气工程与系统科学 2021-07-26 Devaraja Adiga , Rishabh Kumar , Amrith Krishna , Preethi Jyothi , Ganesh Ramakrishnan , Pawan Goyal

One of the significant challenges of Machine Translation (MT) is the scarcity of large amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as resource-rich languages, both Neural Machine Translation…

计算与语言 · 计算机科学 2023-03-06 Amit Kumar , Rupjyoti Baruah , Ajay Pratap , Mayank Swarnkar , Anil Kumar Singh

Automatic n-gram based metrics such as ROUGE are widely used for evaluating generative tasks such as summarization. While these metrics are considered indicative (even if imperfect) of human evaluation for English, their suitability for…

计算与语言 · 计算机科学 2025-07-14 Itai Mondshine , Tzuf Paz-Argaman , Reut Tsarfaty

The phenomenon of compounding is ubiquitous in Sanskrit. It serves for achieving brevity in expressing thoughts, while simultaneously enriching the lexical and structural formation of the language. In this work, we focus on the Sanskrit…

Translating technical terms into lexically similar, low-resource Indian languages remains a challenge due to limited parallel data and the complexity of linguistic structures. We propose a novel use-case of Sanskrit-based segments for…

计算与语言 · 计算机科学 2026-03-26 Karthika N J , Krishnakant Bhatt , Ganesh Ramakrishnan , Preethi Jyothi

Poetry generation in Sanskrit typically requires the verse to be semantically coherent and adhere to strict prosodic rules. In Sanskrit prosody, every line of a verse is typically a fixed length sequence of syllables adhering to prescribed…

计算与语言 · 计算机科学 2026-03-26 Manoj Balaji Jagadeeshan , Atul Singh , Nallani Chakravartula Sahith , Amrith Krishna , Pawan Goyal

Are $n$-gram language models still relevant in this era of neural large language models (LLMs)? Our answer is yes, and we showcase their values in both text analysis and improving neural LLMs. This was done by modernizing $n$-gram LMs in…

计算与语言 · 计算机科学 2025-04-08 Jiacheng Liu , Sewon Min , Luke Zettlemoyer , Yejin Choi , Hannaneh Hajishirzi

The science of versification and analysis of verse in Sanskrit is governed by rules of metre or chandas. Such metre-wise classification of verses has numerous uses for scholars and researchers alike, such as in the study of poets and their…

其他计算机科学 · 计算机科学 2014-09-16 N. Rama , Meenakshi Lakshmanan

Word segmentation is the task of inserting or deleting word boundary characters in order to separate character sequences that correspond to words in some language. In this article we propose an approach based on a beam search algorithm and…

计算与语言 · 计算机科学 2018-12-04 Yerai Doval , Carlos Gómez-Rodríguez

Chinese characters have a complex and hierarchical graphical structure carrying both semantic and phonetic information. We use this structure to enhance the text model and obtain better results in standard NLP operations. First of all, to…

计算与语言 · 计算机科学 2014-05-22 Yannis Haralambous

Word completion and word prediction are two important phenomena in typing that benefit users who type using keyboard or other similar devices. They can have profound impact on the typing of disable people. Our work is based on word…

计算与语言 · 计算机科学 2016-02-26 Md. Masudul Haque , Md. Tarek Habib , Md. Mokhlesur Rahman

Recognition of ancient Tamil characters has always been a challenge for epigraphers. This is primarily because the language has evolved over the several centuries and the character set over this time has both expanded and diversified. This…

计算机视觉与模式识别 · 计算机科学 2019-07-12 Lalitha Giridhar , Aishwarya Dharani and , Velmathi Guruviah

Comprehensively searching for words in Sanskrit E-text is a non-trivial problem because words could change their forms in different contexts. One such context is sandhi or euphonic conjunctions, which cause a word to change owing to the…

计算与语言 · 计算机科学 2019-08-17 S. V. Kasmir Raja , V. Rajitha , Meenakshi Lakshmanan

This paper proposes methods of predicting dynamic time series (including non-stationary ones) based on a linguistic approach, namely, the study of occurrences and repetition of so-called N-grams. This approach is used in computational…

数值分析 · 数学 2026-02-26 Dmytro Lande , Volodymyr Yuzefovych , Yevheniia Tsybulska

Recently, the supervised learning paradigm's surprisingly remarkable performance has garnered considerable attention from Sanskrit Computational Linguists. As a result, the Sanskrit community has put laudable efforts to build task-specific…

计算与语言 · 计算机科学 2021-04-02 Jivnesh Sandhan , Om Adideva , Digumarthi Komal , Laxmidhar Behera , Pawan Goyal

Tree adjoining grammars (TAGs) provide an ample tool to capture syntax of many Indian languages. Tamil represents a special challenge to computational formalisms as it has extensive agglutinative morphology and a comparatively difficult…

计算与语言 · 计算机科学 2017-04-20 Vijay Krishna Menon , S Rajendran , M Anandkumar , K P Soman

We propose a novel framework to understand the text by converting sentences or articles into video-like 3-dimensional tensors. Each frame, corresponding to a slice of the tensor, is a word image that is rendered by the word's shape. The…

计算与语言 · 计算机科学 2021-11-08 Bin Liu , Guosheng Yin , Wenbin Du

With the availability of virtually infinite number text documents in digital format, automatic comparison of textual data is essential for extracting meaningful insights that are difficult to identify manually. Many existing tools,…

信息检索 · 计算机科学 2025-03-25 Akhil Joshi , Sai Teja Erukude , Lior Shamir

The task of automatically identifying a language used in a given text is called Language Identification (LI). India is a multilingual country and many Indians especially youths are comfortable with Hindi and English, in addition to their…

计算与语言 · 计算机科学 2022-11-21 H. L. Shashirekha , F. Balouchzahi , M. D. Anusha , G. Sidorov