paper-with-me

Papers

Subcharacter Information in Japanese Embeddings: When Is It Worth It?

2018-07-01 · WS 2018 7 · Marzena Karpinska, Bofang Li, Anna Rogers, Aleks Drozd, R

Languages with logographic writing systems present a difficulty for traditional character-level models. Leveraging the subcharacter information was recently shown to be beneficial for a number of intrinsic and extrinsic tasks in Chinese. We examine whether the same strategies could be applied for Japanese, and contribute a new analogy dataset for this language.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Text Classification

Similar Papers 제목 키워드 기반

New Perspectives in Sinographic Language Processing Through the Use of Character Structure

2014-05-21 · Yannis Haralambous

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…

Relationtext-classificationText Classification

Joint Embeddings of Chinese Words, Characters, and Fine-grained Subcharacter Components

2017-09-01 · EMNLP 2017 9 · Jinxing Yu, Xun Jian, Hao Xin, Yangqiu Song

Word embeddings have attracted much attention recently. Different from alphabetic writing systems, Chinese characters are often composed of subcharacter components which are also semantically informative. In this work, w…

Named Entity Recognition (NER)Question AnsweringSentiment AnalysisText Classification+2

SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models

2026-04-14 · SungHo Kim, Juhyeong Park, Eda Atalay, SangKeun Lee arxiv

Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units known as Jamo. These subcharacters not only determine the visual structure…

Natural Language Understanding

Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization

2026-03-13 · Mengjie Zhao, Lianbo Liu, Yusuke Fujita, Hao Shi 외 arxiv

SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This mismatch is particularly pronounced in …

Text-To-Speech Synthesis

Utilizing Visual Forms of Japanese Characters for Neural Review Classification

2017-11-01 · IJCNLP 2017 11 · Yota Toyama, Makoto Miwa, Yutaka Sasaki

We propose a novel method that exploits visual information of ideograms and logograms in analyzing Japanese review documents. Our method first converts font images of Japanese characters into character embeddings using c…

ClassificationGeneral ClassificationSentence