Kuntharrgyal Khysru^1,*, Jianguo Wei^1,2, Jianwu Dang³

CMC-Computers, Materials & Continua, Vol.73, No.3, pp. 4897-4907, 2022, DOI:10.32604/cmc.2022.027591 - 28 July 2022

Abstract In China, Tibetan is usually divided into three major dialects: the Am-do, Khams and Lhasa dialects. The Am-do dialect evolved from ancient Tibetan and is a local variant of modern Tibetan. Although this dialect has its own specific historical and social conditions and development, there have been different degrees of communication with other ethnic groups, but all the abovementioned dialects developed from the same language: Tibetan. This paper uses the particularity of Tibetan suffixes in pronunciation and proposes a lexicon for the Am-do language, which optimizes the problems existing in previous research. Audio data of… More >

AnJian-CaiRang^1,2, Dawei Song^3,4,*

Journal on Artificial Intelligence, Vol.4, No.2, pp. 85-98, 2022, DOI:10.32604/jai.2022.029141 - 18 July 2022

Abstract Sorting the Tibetan language quickly and accurately requires first identifying the component elements that make up Tibetan syllables and then sorting by the priority of the component. Based on the study of Tibetan text structure, grammatical rules and syllable structure, we present a structure-based Tibetan syllable recognition method that uses syllable structure instead of grammar. This method avoids complicated Tibetan grammar and recognizes the components of Tibetan syllables simply and quickly. On the basis of identifying the components of Tibetan syllables, a Tibetan syllable sorting algorithm that conforms to the language sorting rules is proposed.… More >

Xiaodong Yan^1,2, Yiqin Wang^1,2, Wei Song^1,2,*, Xiaobing Zhao^1,2, A. Run³, Yang Yanxing⁴

CMC-Computers, Materials & Continua, Vol.73, No.1, pp. 1769-1781, 2022, DOI:10.32604/cmc.2022.027301 - 18 May 2022

Abstract Text summarization creates subset that represents the most important or relevant information in the original content, which effectively reduce information redundancy. Recently neural network method has achieved good results in the task of text summarization both in Chinese and English, but the research of text summarization in low-resource languages is still in the exploratory stage, especially in Tibetan. What’s more, there is no large-scale annotated corpus for text summarization. The lack of dataset severely limits the development of low-resource text summarization. In this case, unsupervised learning approaches are more appealing in low-resource languages as they… More >

Zhijie Wang¹, Yue Zhao^1,*, Licheng Wu¹, Xiaojun Bi¹, Zhuoma Dawa², Qiang Ji³

CMC-Computers, Materials & Continua, Vol.73, No.1, pp. 629-639, 2022, DOI:10.32604/cmc.2022.027092 - 18 May 2022

Abstract As one of Chinese minority languages, Tibetan speech recognition technology was not researched upon as extensively as Chinese and English were until recently. This, along with the relatively small Tibetan corpus, has resulted in an unsatisfying performance of Tibetan speech recognition based on an end-to-end model. This paper aims to achieve an accurate Tibetan speech recognition using a small amount of Tibetan training data. We demonstrate effective methods of Tibetan end-to-end speech recognition via cross-language transfer learning from three aspects: modeling unit selection, transfer learning method, and source language selection. Experimental results show that the More >

Yuan Sun^1,2,*, Chaofan Chen^1,2, Andong Chen³, Xiaobing Zhao^1,2

CMC-Computers, Materials & Continua, Vol.68, No.3, pp. 3203-3213, 2021, DOI:10.32604/cmc.2021.016517 - 06 May 2021

Abstract As the dual task of question answering, question generation (QG) is a significant and challenging task that aims to generate valid and fluent questions from a given paragraph. The QG task is of great significance to question answering systems, conversational systems, and machine reading comprehension systems. Recent sequence to sequence neural models have achieved outstanding performance in English and Chinese QG tasks. However, the task of Tibetan QG is rarely mentioned. The key factor impeding its development is the lack of a public Tibetan QG dataset. Faced with this challenge, the present paper first collects… More >

Feng Liu^1,2,3, Zilan Ma^1,2,3, Marcos A. Caraballo-Ortiz⁴, Hui Zhang⁵, Xu Su^1,2,3, Yuping Liu^1,2,3,*

Phyton-International Journal of Experimental Botany, Vol.89, No.4, pp. 1083-1090, 2020, DOI:10.32604/phyton.2020.011239 - 09 November 2020

Abstract Pedicularis longiflora var. tubiformis (Orobanchaceae) is an abundant parasitic herb mainly found in the Xiaopohu wetland of the Qinghai Lake Basin in Northwestern China. The species has an important local medicinal value, and in this study, we evaluated the chemical profile of its stems, leaves and seeds using mass spectrometry. Dried samples of stems, leaves and seeds were grinded, weighted, and used for a series of extractions with an ultrasonic device at room temperature. The chemical profiles for each tissue were determined using Gas Chromatography-Mass Spectrometry (GC-MS) and Liquid ChromatographyMass Spectrometry (LC-MS). Twenty-seven amino acids and organic… More >

Yue Zhao¹, Jianjian Yue¹, Wei Song^1,*, Xiaona Xu¹, Xiali Li¹, Licheng Wu¹, Qiang Ji²

Journal on Internet of Things, Vol.1, No.1, pp. 17-23, 2019, DOI:10.32604/jiot.2019.05866

Abstract We proposed a method using latent regression Bayesian network (LRBN) to extract the shared speech feature for the input of end-to-end speech recognition model. The structure of LRBN is compact and its parameter learning is fast. Compared with Convolutional Neural Network, it has a simpler and understood structure and less parameters to learn. Experimental results show that the advantage of hybrid LRBN/Bidirectional Long Short-Term Memory-Connectionist Temporal Classification architecture for Tibetan multi-dialect speech recognition, and demonstrate the LRBN is helpful to differentiate among multiple language speech sets. More >

Zhijuan Wang^1,2, Xiaobin Zhao^1,2, Wei Song^1,*, Antai Wang³

CMC-Computers, Materials & Continua, Vol.61, No.1, pp. 213-225, 2019, DOI:10.32604/cmc.2019.05690

Abstract Readability is a fundamental problem in textbooks assessment. For low re-sources languages (LRL), however, little investigation has been done on the readability of textbook. In this paper, we proposed a readability assessment method for Tibetan textbook (a low resource language). We extract features based on the information that are gotten by Tibetan segmentation and named entity recognition. Then, we calculate the correlation of different features using Pearson Correlation Coefficient and select some feature sets to design the readability formula. Fit detection, F test and T test are applied on these selected features to generate a More >

Yue Zhao¹, Jianjian Yue¹, Wei Song^1,*, Xiaona Xu¹, Xiali Li¹, Licheng Wu¹, Qiang Ji²

CMC-Computers, Materials & Continua, Vol.60, No.3, pp. 1223-1235, 2019, DOI:10.32604/cmc.2019.05636

Abstract Tibetan language has very limited resource for conventional automatic speech recognition so far. It lacks of enough data, sub-word unit, lexicons and word inventories for some dialects. And speech content recognition and dialect classification have been treated as two independent tasks and modeled respectively in most prior works. But the two tasks are highly correlated. In this paper, we present a multi-task WaveNet model to perform simultaneous Tibetan multi-dialect speech recognition and dialect identification. It avoids processing the pronunciation dictionary and word segmentation for new dialects, while, in the meantime, allows training speech recognition and More >

Xiaodong Yan^1,2, Wei Song^1,2,*, Xiaobing Zhao^1,2, Anti Wang³

CMC-Computers, Materials & Continua, Vol.60, No.2, pp. 707-719, 2019, DOI:10.32604/cmc.2019.05157

Abstract We apply the semi-supervised recursive autoencoders (RAE) model for the sentiment classification task of Tibetan short text, and we obtain a better classification effect. The input of the semi-supervised RAE model is the word vector. We crawled a large amount of Tibetan text from the Internet, got Tibetan word vectors by using Word2vec, and verified its validity through simple experiments. The values of parameter α and word vector dimension are important to the model effect. The experiment results indicate that when α is 0.3 and the word vector dimension is 60, the model works best. More >