FSPRM: A Feature Subsequence Based Probability Representation Model for Chinese Word Embedding

Zhang, Yun; Liu, Yongguo; Zhu, Jiajing; Wu, Xindong

doi:10.1109/taslp.2021.3073868

Cited by 7 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Strokes are the most fine-grained units in Chinese characters, and each Chinese character can be decomposed into a sequence of strokes with a specific order. According to the inspiration of [29], we categorize strokes into five types: horizontal, vertical, apostrophe, dot, and fold, which are also the five basic types of strokes stipulated in the "Common Character List of Modern Chinese" jointly issued by several Chinese cultural departments in 1988. We coded these 5 types of strokes as shown in Table 2.…”

Section: Methodsmentioning

confidence: 99%

Attention-enabled Multi-layer Subword Joint Learning for Chinese Word Embedding

Xue,

Tan,

Xiong

et al. 2024

Preprint

View full text Add to dashboard Cite

In recent years, Chinese word embeddings have attracted significant attention in the field of natural language processing (NLP). The complex structures and diverse influences of Chinese characters present distinct challenges for semantic representation. As a result, Chinese word embeddings are primarily investigated in conjunction with characters and their subcomponents. Previous research has demonstrated that word vectors frequently fail to capture the subtle semantics embedded within the complex structure of Chinese characters. Furthermore, they often neglect the varying contributions of subword information to semantics at different levels. To tackle these challenges, we present a weight-based word vector model that takes into account the internal structure of Chinese words at various levels. The model further categorizes the internal structure of Chinese words into six layers of subword information: words, characters, components, pinyin, strokes, and structures. The semantics of Chinese words can be derived by integrating the subword information from various layers. Moreover, the model considers the varying contributions of each subword layer to the semantics of Chinese words. It utilizes an attention mechanism to determine the weights between and within the subword layers, facilitating the comprehensive extraction of word semantics. The word-level subwords act as the attention mechanism query for subwords in other layers to learn semantic bias. Experimental results show that the proposed word vector model achieves enhancements in various evaluation metrics, such as word similarity, word analogy, text categorization, and case studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Attention-enabled Multi-layer Subword Joint Learning for Chinese Word Embedding

Xue,

Tan,

Xiong

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“… Chuang et al ( 2021 ) Automatic speech recognition and translation system LibriSpeech corpus, Augmented LibriSpeech, Fisher Spanish corpora LSTM, BiLSTM, CNN Word2Vec, fastText Word2Vec model efficiently maps speech signals to semantic space 7. Zhang et al ( 2021 ) Chinese word representation SogouCA data, Wikipedia dump, Fudan dataset LSTM Word2Vec, GloVe, BERT, CWE LSTM + CWE achieves an F1-score of 95.53% for the NER task 8. Shekhar et al ( 2019 ) English-Hindi mixed languages text identification Dataset ICON 2016, Forum for IR Evaluation 2014 shared task on transliterated search, MSIR 2015, 2016 BiLSTM Word2Vec, Character and word embedding BiLSTM + Word2Vec achieves an F1-score of 83.9% for the NER task 9.…”

Section: Appendix Amentioning

confidence: 99%

“…The Chinese word embedding-based model with LSTM acquires an F1-score of 95.53% to understand the semantics of words and efficiently analyze the features. (Zhang et al 2021). A domain-specific word embedding approach with a fuzzy metric that focuses on a unique entity recognition task is proposed to adopt cooking recipes from a set of all available recipes.…”

Section: Named Entity Recognition and Recommendation Systemmentioning

confidence: 99%

Impact of word embedding models on text analytics in deep learning environment: a review

2023

View full text Add to dashboard Cite

The selection of word embedding and deep learning models for better outcomes is vital. Word embeddings are an n-dimensional distributed representation of a text that attempts to capture the meanings of the words. Deep learning models utilize multiple computing layers to learn hierarchical representations of data. The word embedding technique represented by deep learning has received much attention. It is used in various natural language processing (NLP) applications, such as text classification, sentiment analysis, named entity recognition, topic modeling, etc. This paper reviews the representative methods of the most prominent word embedding and deep learning models. It presents an overview of recent research trends in NLP and a detailed understanding of how to use these models to achieve efficient results on text analytics tasks. The review summarizes, contrasts, and compares numerous word embedding and deep learning models and includes a list of prominent datasets, tools, APIs, and popular publications. A reference for selecting a suitable word embedding and deep learning approach is presented based on a comparative analysis of different techniques to perform text analytics tasks. This paper can serve as a quick reference for learning the basics, benefits, and challenges of various word representation approaches and deep learning models, with their application to text analytics and a future outlook on research. It can be concluded from the findings of this study that domain-specific word embedding and the long short term memory model can be employed to improve overall text analytics task performance.

show abstract

Exploring Chinese word embedding with similar context and reinforcement learning

Zhang

Liu

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

FSPRM: A Feature Subsequence Based Probability Representation Model for Chinese Word Embedding

Cited by 7 publications

References 36 publications

Attention-enabled Multi-layer Subword Joint Learning for Chinese Word Embedding

Attention-enabled Multi-layer Subword Joint Learning for Chinese Word Embedding

Impact of word embedding models on text analytics in deep learning environment: a review

Exploring Chinese word embedding with similar context and reinforcement learning

Contact Info

Product

Resources

About