Search

Chinese word embedding has attracted considerable attention in the field of natural language processing. Existing methods model the relation between target and neighbouring contextual words. However, with the phenomenon of irrelevant neighbouring words in Chinese, these methods are limited in capturing and understanding the semantics of Chinese words. In this study, we designed sc2vec to explore Chinese word embeddings by proposing a similar context to reduce the influence of the above problem and comprehend relevant semantics of Chinese words. Meanwhile, to enhance the learning architecture, sc2vec was modelled with reinforcement learning to generate high-quality Chinese word embeddings, regarding continuous bag-of-words and skip-gram models as two actions of an agent over a corpus. The results on word analogy, word similarity, named entity recognition, and text classification tasks demonstrate that the proposed model outperforms most state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

As an important task in Asian language information processing, Chinese word embedding learning has attracted much attention recently. Based on either Skip-gram or CBOW, several methods have been proposed to exploit Chinese characters and sub-character components for learning Chinese word embeddings. Chinese characters are combinations of meaning, structure, and phonetic information (pinyin). However, previous works only cover the former two aspects and cannot effectively explore distinct semantics of characters. To address this issue, we develop a Pinyin-enhance Skip-gram model named rsp2vec, in addition to a radical and pinyin-enhanced Chinese word embedding (rPCWE) learning models based on CBOW. For our models, the phonetic information and semantic components of Chinese characters are encoded into embeddings simultaneously. Evaluations on word analogy reasoning, word relevance, text classification, named entity recognition, and case studies validate the effectiveness of our models. [ABSTRACT FROM AUTHOR]

With the advent of the 5G and Artificial Intelligence of Things (AIoT) era, related technologies such as the Internet of Things, big data analysis, cloud applications, and artificial intelligence have brought broad prospects to many application fields, such as smart homes, autonomous vehicles, smart cities, healthcare, and smart campus. At present, most university campus app is presented in the form of static web pages or app menus. This study mainly developed a Deep Neural Network (DNN) based emotionally aware campus virtual assistant. The main contributions of this research are: (1) This study introduces the Chinese Word Embedding to the robot dialogue system, effectively improving dialogue tolerance and semantic interpretation. (2) The traditional method of emotion identification must first tokenize the Chinese sentence, analyze the clauses and part of speech, and capture the emotional keywords before being interpreted by the expert system. Different from the traditional method, this study classifies the input directly through the convolutional neural network after the input sentence is converted into a spectrogram by Fourier Transform. (3) This study is presented in App mode, which is easier to use and economical. (4) This system provides a simple voice response interface, without the need for users to find information in complex web pages or app menus.

Word embedding refers to mapping words or phrases to vectors of real numbers. This is the precondition of text classification, sentiment analysis and text mining in natural language processing using deep neural networks. Taking English as an example, most of current word embedding algorithms obtain the vectors by learning the distribution of word's prefix, suffix, etyma and the entire word itself. Unlike English, Chinese words are composed of components and strokes. Furthermore, those components and strokes usually hint the meaning of the word. Thus, components and strokes distribution must be fully considered and learnt when one's doing Chinese word embedding. In this paper, we propose a component-based cascade n-gram (CBC n-gram) model and a stroke-based cascade n-gram (SBC n-gram) model. By overlaying component and stroke n-gram vectors on word vectors, we successfully improve Chinese word embedding so as to preserve as more morphological information as possible at different granularity levels. We evaluate our models on word similarity, word analogy and text classification tasks using wordsim-240, wordsim-296, Chinese word analogy dataset and Fudan Corpus, respectively. Experimental and comparison results show that our models outperform other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The most common method of word embedding is to learn word vector representations from context information of large-scale text. However, Chinese words usually consist of characters, subcharacters, and strokes, and each part contains rich semantic information. The quality of Chinese word vectors is related to the accuracy of prediction. Therefore, to obtain high-quality Chinese character embedding, we propose a continuously enhanced word embedding model. The model starts with fine-grained strokes and adjacent stroke information and enhances subcharacter embedding by combining the relationship vector representation between strokes. Similarly, we combine the subcharacter relationship vector and the character relationship vector to learn Chinese word embedding based on the enhanced subcharacter embedding. We construct the underlying stroke n-grams and adjacent stroke n-grams and extract the relationship vector used to enhance the relationship between the components, which can be used to learn Chinese word embedding and improve the accuracy. Finally, we evaluate our model on the word similarity calculations and word reasoning tasks.

Co-occurrence information between words is the basis of training word embeddings; besides, Chinese characters are composed of subcharacters, words made up by the same characters or subcharacters usually have similar semantics, but this internal substructure information is usually neglected in popular models. In this paper, we propose a novel method for learning Chinese word embeddings, which takes full use of external co-occurrence context information and internal substructure information. We represent each word as a bag of subcharacter n-grams, and our model learns the vector representation corresponding to the word and its subcharacter n-grams. The final word embeddings are represented as the sum of these two kinds of vector representation, which makes the learned word embeddings can take into account both the internal structure information and external co-occurrence information possible. The experiments show that our method outperforms state-of-the-art performance on benchmarks.