Radical Embedding: Delving Deeper to Chinese Radicals

Shi, Xiaohu; Zhai, Junjie; Yang, Xudong; Xie, Zehua; Liu, Chao

doi:10.3115/v1/p15-2098

Cited by 65 publications

(59 citation statements)

References 7 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In alphabetic languages, sub-word units are easy to identify, whereas in logographic languages, a similar effect can be achieved only if sub-character level information is taken into consideration. 1 Having noticed this significant difference between these two writing systems, Shi et al (2015), Liu et al (2017), Peng et al (2017), and Cao et al (2017) used stroke-level information for logographic languages when constructing word embeddings; Toyama et al (2017) used visual information for strokes and Japanese Kanji radicals in a text classification task. 2 Some studies have performed NMT tasks using various sub-word "equivalents".…”

Section: Introductionmentioning

confidence: 99%

Neural Machine Translation of Logographic Language Using Sub-character Level Information

Zhang¹,

Komachi²

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

View full text Add to dashboard Cite

Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages.Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.1 Taking the ASPEC corpus as an example, the average word lengths are roughly 1.5 characters (Chinese words, tokenized by Jieba tokenizer), 1.7 characters (Japanese words, tokenized by MeCab tokenizer), and 5.7 characters (English words, tokenized by Moses tokenizer), respectively. Therefore, when a sub-word model of similar vocabulary size is applied directly, English sub-words usually contain several letters, which are more effective in facilitating NMT, whereas Chinese and Japanese sub-words are largely just characters.2. We facilitate the encoding or decoding process by using sub-character sequences on either the source or target side of the NMT system. This will improve translation performance; if sub-character information is shared between the encoder and decoder, it will further benefit the NMT system.3. Specifically, Chinese ideograph 4 data and Japanese stroke data are the best choices for relevant NMT tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural Machine Translation of Logographic Language Using Sub-character Level Information

Zhang¹,

Komachi²

2018

Proceedings of the Third Conference on Machine Translation: Research Papers

View full text Add to dashboard Cite

show abstract

“…After that, Chen et al (2015) argued that the semantic meaning of a word was also related to the meanings of its composing characters, and the word embeddings could be enhanced with the help of the context characters. After that, Shi et al (2015) made a tentative exploration about radicals, and demonstrated the utility of radicals in some conditions. Furthermore, some methods were proposed to use radical information to strengthen Chinese word embedding (Yin et al 2016;Yu et al 2017), but the scope of their research on radicals was still limited to the embedding problem.…”

Section: Related Workmentioning

confidence: 99%

A Radical-Aware Attention-Based Model for Chinese Text Classification

Tao

Tong

Zhao

et al. 2019

AAAI

View full text Add to dashboard Cite

Recent years, Chinese text classification has attracted more and more research attention. However, most existing techniques which specifically aim at English materials may lose effectiveness on this task due to the huge difference between Chinese and English. Actually, as a special kind of hieroglyphics, Chinese characters and radicals are semantically useful but still unexplored in the task of text classification. To that end, in this paper, we first analyze the motives of using multiple granularity features to represent a Chinese text by inspecting the characteristics of radicals, characters and words. For better representing the Chinese text and then implementing Chinese text classification, we propose a novel Radicalaware Attention-based Four-Granularity (RAFG) model to take full advantages of Chinese characters, words, characterlevel radicals, word-level radicals simultaneously. Specifically, RAFG applies a serialized BLSTM structure which is context-aware and able to capture the long-range information to model the character sharing property of Chinese and sequence characteristics in texts. Further, we design an attention mechanism to enhance the effects of radicals thus model the radical sharing property when integrating granularities. Finally, we conduct extensive experiments, where the experimental results not only show the superiority of our model, but also validate the effectiveness of radicals in the task of Chinese text classification.

show abstract

“…Based on the linguistic features of Chinese, recent methods have used the character information to improve Chinese word embeddings. These methods can be categorized into two kinds: 1) One kind of methods learn word embeddings with its constituent character (Chen et al, 2015), radical 2 (Shi et al, 2015;Yin et al, 2016; or strokes 3 (Cao et al, 2018). However, these methods usually use simple operations, such as averaging and n-gram, to model the inherent compositionality within a word, which is not enough to handle the complicated linguistic compositionality.…”

Section: Introductionmentioning

confidence: 99%

Untitled

Sun

Qiu

Huang

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information. In this paper, we propose a model to learn Chinese word embeddings via three-level composition: (1) a convolutional neural network to extract the intra-character compositionality from the visual shape of a character; (2) a recurrent neural network with self-attention to compose character representation into word embeddings; (3) the Skip-Gram framework to capture noncompositionality directly from the contextual information. Evaluations demonstrate the superior performance of our model on four tasks: word similarity, sentiment analysis, named entity recognition and part-of-speech tagging. 1

show abstract

Radical Embedding: Delving Deeper to Chinese Radicals

Cited by 65 publications

References 7 publications

Neural Machine Translation of Logographic Language Using Sub-character Level Information

Neural Machine Translation of Logographic Language Using Sub-character Level Information

A Radical-Aware Attention-Based Model for Chinese Text Classification

Untitled

Contact Info

Product

Resources

About