English
Related papers

Related papers: A Sub-Character Architecture for Korean Language P…

200 papers

Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et…

Computation and Language · Computer Science 2019-03-04 Longtu Zhang , Mamoru Komachi

Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens. This process known as tokenization relies on a pre-built vocabulary of words or sub-word morphemes.…

Computation and Language · Computer Science 2023-05-31 Li Sun , Florian Luisier , Kayhan Batmanghelich , Dinei Florencio , Cha Zhang

In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the…

Computation and Language · Computer Science 2019-04-12 Jorge A. Balazs , Yutaka Matsuo

Pre-trained Language Models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. Various Chinese PLMs have been successively proposed for learning better Chinese language…

Computation and Language · Computer Science 2022-09-16 Borun Chen , Hongyin Tang , Jiahao Bu , Kai Zhang , Jingang Wang , Qifan Wang , Hai-Tao Zheng , Wei Wu , Liqian Yu

This memoir explores two fundamental aspects of Natural Language Processing (NLP): the creation of linguistic resources and the evaluation of NLP system performance. Over the past decade, my work has focused on developing a morpheme-based…

Computation and Language · Computer Science 2026-02-16 Jungyeul Park

Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over discrete units called tokens. To represent text, the vast majority of LLMs use words or word fragments as the…

Translating characters instead of words or word-fragments has the potential to simplify the processing pipeline for neural machine translation (NMT), and improve results by eliminating hyper-parameters and manual feature engineering.…

Computation and Language · Computer Science 2018-08-30 Colin Cherry , George Foster , Ankur Bapna , Orhan Firat , Wolfgang Macherey

Historical records in Korea before the 20th century were primarily written in Hanja, an extinct language based on Chinese characters and not understood by modern Korean or Chinese speakers. Historians with expertise in this time period have…

Computation and Language · Computer Science 2022-10-12 Haneul Yoo , Jiho Jin , Juhee Son , JinYeong Bak , Kyunghyun Cho , Alice Oh

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens. In this work, we…

Computation and Language · Computer Science 2025-06-13 Tatsuya Hiraoka , Kentaro Inui

The use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a…

Computation and Language · Computer Science 2019-05-07 Yi Zhu , Ivan Vulić , Anna Korhonen

Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into…

Computation and Language · Computer Science 2021-05-17 Wentao Ma , Yiming Cui , Chenglei Si , Ting Liu , Shijin Wang , Guoping Hu

B-Prolog is a high-performance implementation of the standard Prolog language with several extensions including matching clauses, action rules for event handling, finite-domain constraint solving, arrays and hash tables, declarative loop…

Programming Languages · Computer Science 2011-03-07 Neng-Fa Zhou

Tables are a primary medium for conveying critical information in administrative domains, yet their complexity hinders utilization by Large Language Models (LLMs). This paper introduces the Theme-Explanation Structure-based Table…

Computation and Language · Computer Science 2025-07-10 TaeYoon Kwack , Jisoo Kim , Ki Yong Jung , DongGeon Lee , Heesun Park

This paper introduces UniDive for Korean, an integrated framework that bridges Universal Dependencies (UD) and Universal Morphology (UniMorph) to enhance the representation and processing of Korean {morphosyntax}. Korean's rich inflectional…

Computation and Language · Computer Science 2025-03-28 Jungyeul Park , Yige Chen , Kyuwon Kim , KyungTae Lim , Chulwoo Park

The choice of modeling units is crucial for automatic speech recognition (ASR) tasks. In mandarin scenarios, the Chinese characters represent meaning but are not directly related to the pronunciation. Thus only considering the writing of…

Computation and Language · Computer Science 2022-10-19 Yuting Yang , Binbin Du , Yuke Li

Common Large Language model (LLM) evaluations rely on demonstration examples to steer models' responses to the desired style. While the number of examples used has been studied and standardized, the choice of how to format examples is less…

Computation and Language · Computer Science 2025-10-08 Jingtong Su , Jianyu Zhang , Karen Ullrich , Léon Bottou , Mark Ibrahim

Recent advances in large language models using deep learning techniques have renewed interest on how languages can be learned from data. However, it is unclear whether or how these models represent grammatical information from the learned…

Computation and Language · Computer Science 2024-02-20 Jérôme Michaud , Anna Jon-and

We present a Coq formalisation of the small-step operational semantics of Jafun, a small Java-like language with classes. This format of semantics makes it possible to naturally specify and prove invariants that should hold at each…

Logic in Computer Science · Computer Science 2018-08-17 Aleksy Schubert , Jacek Chrząszcz

The glyphic writing system of Chinese incorporates information-rich visual features in each character, such as radicals that provide hints about meaning or pronunciation. However, there has been no investigation into whether contemporary…

Computation and Language · Computer Science 2025-01-31 Xiaofeng Wu , Karl Stratos , Wei Xu

Chinese character recognition has attracted much research interest due to its wide applications. Although it has been studied for many years, some issues in this field have not been completely resolved yet, e.g. the zero-shot problem.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Jingye Chen , Bin Li , Xiangyang Xue
‹ Prev 1 4 5 6 7 8 10 Next ›