paper-with-me

홈 › Papers

Glyph-aware Embedding of Chinese Characters

2017-08-31 · WS 2017 9 · Falcon Z. Dai, Zheng Cai

Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character's glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to incorporate the spatio-structural patterns of Chinese glyphs as rendered in raw pixels. In the context of two basic Chinese NLP tasks of language modeling and word segmentation, the model learns to represent each character's task-relevant semantic and syntactic information in the character-level embedding.

📄 PDF Abstract BibTeX arXiv:1709.00028

Code (1)

falcondai/chinese-char-lm 공식 구현 tf

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph

2021-07-01 · Yunxin Li, Yu Zhao, Baotian Hu, Qingcai Chen 외

Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters. The typical method to utilize the glyph features …

Learning Chinese Word Representations From Glyphs Of Characters

2017-08-16 · EMNLP 2017 9 · Tzu-Ray Su, Hung-Yi Lee

In this paper, we propose new methods to learn Chinese word representations. Chinese characters are composed of graphical components, which carry rich semantics. It is common for a Chinese learner to comprehend the meani…

Glyph2Vec: Learning Chinese Out-of-Vocabulary Word Embedding from Glyphs

2020-07-01 · ACL 2020 6 · Hong-You Chen, Sz-Han Yu, Shou-De Lin

Chinese NLP applications that rely on large text often contain huge amounts of vocabulary which are sparse in corpus. We show that characters{'} written form, \textit{Glyphs}, in ideographic languages could carry rich se…

Chinese Embedding via Stroke and Glyph Information: A Dual-channel View

2019-06-03 · Hanqing Tao, Shiwei Tong, Tong Xu, Qi Liu 외

Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings. In this paper, we argue that Chinese word embeddings can be substantially enriched by the morphological infor…

Word EmbeddingsWord Similarity

ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information

2021-06-30 · ACL 2021 5 · Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng 외

Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we …

Language ModelingLanguage ModellingMachine Reading ComprehensionNamed Entity Recognition+5