中文
相关论文

相关论文: Unsupervised Separation of Native and Loanwords fo…

200 篇论文

When looking at the structure of natural language, "phrases" and "words" are central notions. We consider the problem of identifying such "meaningful subparts" of language of any length and underlying composition principles in a completely…

计算与语言 · 计算机科学 2016-02-19 Stefan Gerdjikov , Klaus U. Schulz

We present two methods for unsupervised segmentation of words into morpheme-like units. The model utilized is especially suited for languages with a rich morphology, such as Finnish. The first method is based on the Minimum Description…

计算与语言 · 计算机科学 2007-05-23 Mathias Creutz , Krista Lagus

We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text…

计算与语言 · 计算机科学 2019-01-08 Yunsu Kim , Julian Schamper , Hermann Ney

Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples that represent a given…

计算与语言 · 计算机科学 2025-02-19 Abdellah El Mekki , Muhammad Abdul-Mageed

Topics models, such as LDA, are widely used in Natural Language Processing. Making their output interpretable is an important area of research with applications to areas such as the enhancement of exploratory search interfaces and the…

计算与语言 · 计算机科学 2019-04-01 Areej Alokaili , Nikolaos Aletras , Mark Stevenson

Vision-language models score well on mathematical, scientific, and spatial reasoning benchmarks, yet these evaluations are overwhelmingly English. I present the first cross-lingual visual reasoning audit for Indian languages. 980 questions…

计算与语言 · 计算机科学 2026-03-31 Swastik R

The evolution and diversity of a language is evident from it's various dialects. If the various dialects are not addressed in technological advancements like automatic speech recognition and speech synthesis, there is a chance that these…

音频与语音处理 · 电气工程与系统科学 2024-08-28 M. Nanmalar , P. Vijayalakshmi , T. Nagarajan

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

计算与语言 · 计算机科学 2021-09-03 Chantal Amrhein , Rico Sennrich

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

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the…

计算与语言 · 计算机科学 2023-05-23 Amit Kumar , Shantipriya Parida , Ajay Pratap , Anil Kumar Singh

Following approaches for understanding lexical meaning developed by Yaska, Patanjali and Bhartrihari from Indian linguistic traditions and extending approaches developed by Leibniz and Brentano in the modern times, a framework of formal…

计算与语言 · 计算机科学 2018-08-03 Jyoti Jha , Sreekavitha Parupalli , Navjyoti Singh

Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable…

计算与语言 · 计算机科学 2021-06-10 Yash Khemchandani , Sarvesh Mehtani , Vaidehi Patil , Abhijeet Awasthi , Partha Talukdar , Sunita Sarawagi

Abusive language is a growing concern in many social media platforms. Repeated exposure to abusive speech has created physiological effects on the target users. Thus, the problem of abusive language should be addressed in all forms for…

计算与语言 · 计算机科学 2022-04-28 Mithun Das , Somnath Banerjee , Animesh Mukherjee

Languages evolve over time in a process in which reproduction, mutation and extinction are all possible, similar to what happens to living organisms. Using this similarity it is possible, in principle, to build family trees which show the…

计算与语言 · 计算机科学 2012-07-03 Maurizio Serva

We present a computational analysis of three language varieties: native, advanced non-native, and translation. Our goal is to investigate the similarities and differences between non-native language productions and translations, contrasting…

计算与语言 · 计算机科学 2016-09-13 Ella Rabinovich , Sergiu Nisioi , Noam Ordan , Shuly Wintner

A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a significant amount of the total probability mass of…

计算与语言 · 计算机科学 2022-03-25 Benjamin LeBrun , Alessandro Sordoni , Timothy J. O'Donnell

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…

计算与语言 · 计算机科学 2021-03-15 Xavier Garcia , Aditya Siddhant , Orhan Firat , Ankur P. Parikh

Tokenization is the foundational step in all large language model (LLM) pipelines, yet the dominant approach Byte Pair Encoding (BPE) and its variants is inherently script agnostic and optimized for English like morphology. For…

计算与语言 · 计算机科学 2026-03-09 Prabhu Raja

Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised…

计算与语言 · 计算机科学 2023-12-21 Isidora Chara Tourni , Derry Wijaya

Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine…

计算与语言 · 计算机科学 2016-09-13 Ella Rabinovich , Shuly Wintner