Search

The existing biomedical event trigger detection methods have the following defects: Redundant information unrelated to triggers are retained; potential correlations between entities and events are ignored; traditional methods are vulnerable to data scarcity. A biomedical event trigger detection based on two-stage question answering paradigm is proposed to address the above problems. In the event type identification phase, in order to exclude the interference of irrelevant information, the attention based on syntactic distance is allowed to capture more meaningful contextual features. In order to effectively utilize the potential features in the entities, the word-entity-event co-occurrence feature based on global statistics is used to guide event type aware attention to explore the strong relationship between words and events. In the trigger localization phase, the trigger index of the event in the sentence is answered according to the identified event type questions, thus leveraging the rich question answering database to achieve data enhancement. The results on the MLEE corpus show that the two-stage question answering paradigm, syntactic distance attention, and event type aware attention effectively improve the performance of the model, and the proposed model achieves 81.39% F1-score, outperforming other baseline models in terms of detailed results for multiple event types. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the rapid development of Internet communication and digital technologies, government can create and share travel information through social media. The purpose of this study is to understand how tourism attraction is constructed by government departments on the social media and how social media users perceive these tourism attractions. The technique of text corpus was utilized to analyze the posting messages elected from Tainan City Government's Facebook page─@traveltainan. The research results reveal that 10 types of tourism attraction were identified. In addition, the interactive responses on @traveltainan were also examined in terms of "likes," "comments," and "shares." The findings and suggestions are proposed for future studies and implementations about tourism policy and planning in the local area. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Textbook Research is the property of National Academy for Educational Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In view of the incomplete division of meanings and the lack of accuracy in the definition of “鸡（chicken）” in existing dictionaries, the authors divide the meanings of “鸡（chicken）” by combining the theory of physical structure and corpus technology, so as to improve the accuracy of the description of “鸡（chicken）” and the completeness of the division of meanings. It can be seen that the theory of physical structure provides theoretical support for the division and description of noun meanings, and has important value in improving the completeness, accuracy and systematicness of noun interpretation. [ABSTRACT FROM AUTHOR]

Under the guidance of constructivist teaching theories, the present study proposes a learner-centered teaching model for the translation of discourse with Chinese characteristics based on two self-built corpora: the Chinese-English parallel corpus and the learner parallel corpus of Xi Jinping: The Governance of China. Taking Don Kiraly's constructivist translation teaching principles and Li Zhihou's scaffolding teaching mode as references, the article constructs a corpusbased six-stage teaching model for the translation of discourse with Chinese characteristics, which can be broken into nine steps, with the dual aim of enhancing the students' competence of translating contemporary discourse with Chinese characteristics and cultivating patriotism among the students. [ABSTRACT FROM AUTHOR]

Through corpus analysis, the semantic situation of “他这样做+是+X(+的) is analyzed, and whether X1 type words (the words as 他这样做 ) and X2 type words (the words as 他这样做 ) are added with "" in the construction is discussed. The results show that X2 type words do not need subjective confirmation and semantic transfer, only need to use做 as a connection marker, and then do not add做. The X2 type words are mainly adjective words and have stronger judgment; X1 type words are mainly verbal words and have stronger narrative. The latter can be compatible with 做 in descriptive sentences. Different from X1 type words, the specific semantic behavior orientation of X2 type words is exactly the behavior itself, the nature of the behavior, the cause of the behavior and the purpose of the behavior. [ABSTRACT FROM AUTHOR]

Based on the CCL corpus and the full-text retrieval system of Chinese books, the author investigates the lexicalization process, motivation and mechanism of " (zhishi)” from a diachronic perspective. The results show that the cross-layer structure" (zhishi)" first appeared in the Wei, Jin and Six Dynasties. In the Tang Dynasty, it was lexicalized into adverbs under the joint action of prosodic constraints, the expansion of subsequent components, the change of syntactic position and the increase of frequency of use. Reanalysis is an important mechanism for the lexicalization of “(zhishi)”. Similarly, in the Tang Dynasty, the adverb “ (zhishi)" was also grammaticalized into a conjunction under the mechanism of context absorption. “ (zhishi)" as a cross-layer structure, an adverb and a conjunction is all used in modern Chinese. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The discourse marker function of “不得不说 (budebushou)” is analyzed based on corpus, and the formation of the function is discussed with pragmatic inference and the evolution of modality, semantics, structure and distribution. The core function of the discourse marker “不得不说 (budebushuo)” is to express the speaker’s evaluation or view of things based on objective reasons. Its specific functions can be divided into the interpersonal function of responding to the other ’s point of view and directly evaluating the other party as well as the discourse function of changing the topic to introduce the ensuing text and expressing evaluations on the topic. The discourse marker function of “不得不说 (budebushuo)” was formed in the late Qing Dynasty. It experienced the evolution path of “verbal phrase-adverbial phrase-discourse marker”, and shifted from objective to subjective and passive to active. [ABSTRACT FROM AUTHOR]

In the current software development environment, a large amount of low-quality and meaningless code knowledge hinders developers from code reuse, which greatly reduces the efficiency of software empolder. In order to quickly and accurately recommend high-quality code knowledge for developers, this paper proposed a code snippets recommendation method CSRSB based on SBERT model. Firstly, the method obtained massive high-quality data to build a code corpus. It also generated sentence vectors with rich semantics for the natural language description corresponding to the code snippets and the natural language query input by the user based on the deep learning model SBERT. Then, it implemented code snippets recommendations by comparing the dot product similarity. The effectiveness of the method was verified by comparing the three commonly used recommendation evaluation metrics, Hit Ratio, Mean Reciprocal Rank and Mean Average Precision, with the methods in existing related research. The experimental results show that CSRSB can effectively improve the accuracy of code snippets recommendation and can also achieve fast recommendations. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

“娘（niang）” is originally a appellation for women, but now it contains the semantic features of [± women]. From the diachronic and synchronic perspectives, the author of this paper summarizes and analyzes the emerging nouns or predicate structures with “娘（niang）” as the core in contemporary Chinese corpus, and holds that these structures are mainly manifested in the lexical frame filling formed by extracting the substantive components or word-formation morphemes and the formal frame filling formed by relying on habitual forms. Pragmatically, it mainly has the function of reference and evaluation; emotional color, experienced praise women, despise men’s derogation, and then to today’s women’s self-ridicule and some men’s goodwill description. [ABSTRACT FROM AUTHOR]

“娘 (niang) ” is originally a appellation for women, but now it contains the semantic features of [± women]. From the diachronic and synchronic perspectives, the author of this paper summarizes and analyzes the emerging nouns or predicate structures with “娘（niang）” as the core in contemporary Chinese corpus, and holds that these structures are mainly manifested in the lexical frame filling formed by extracting the substantive components or word-formation morphemes and the formal frame filling formed by relying on habitual forms. Pragmatically, it mainly has the function of reference and evaluation; emotional color, experienced praise women, despise men’s derogation, and then to today’s women’s self-ridicule and some men’s goodwill description. [ABSTRACT FROM AUTHOR]

Based on the corpus analysis, the similarities and differences of the negative expression functions of '一个个的 (yigegede) ' and '一天天的 (yitiantiande) ' are analyzed, and the causes are discussed from the perspectives of semantic features, pragmatic principles and cognitive psychology. The '一个个的 (yigegede) ' involved objects are mostly the ' other group', and there is still a strong entity reference; '一天天的 (yitiantiande) ' has no emphasis on its own side and the other side as well as the singular and the plural, and gradually has little relationship with the meaning of time plural. The causes of negative expression function are as follows: '一个个的 (yigegede) ' and '一天天的 (yitiantiande) ' have plural semantic features, and the number of things more than the norm is likely to cause negative evaluation; the real negative components under the politeness principle are omitted, and after the simplification, '一个个的 (yigegede) ' and '一天天的 (yitiantiande) ' gradually have semantic and syntactic self-sufficiency; compared with other monosyllabic quantifiers, '个 (ge) ' and '天 (tian) ' have prominent characteristics in frequency and semantic function. The functional differences between the two are related to the different characteristics of quantifiers. [ABSTRACT FROM AUTHOR]

Spoken language understanding (SLU) is an important component of dialog system. Recently, pre-trained language model has made breakthrough in various tasks of spoken language understanding. However, these language models are trained with large-scale written language, which are quite different from spoken language in structure, condition and expression pattern. This paper construct large-scale multi-turn bi-role spoken dialog corpus. Then four self-supervised pre-trained tasks are proposed: masked language model, role prediction, intra-query reverse prediction and inter-query exchange prediction. A bert-based spoken dialog language model (SPD-BERT) is pre-trained through multi-task learning. Finally, the model is tested with three typical tasks of intelligent customer service in finance domain. The experiment results demonstrates the effectiveness of out model. [ABSTRACT FROM AUTHOR]

To solve the problem of the existing LSTM extracted feature vectors in named entity recognition tasks with insufficient ability for expressing short-term information features, the LSTM network was proposed based on hierarchical residual connections. The non-linear fitting capability of short-term information features was improved by adding residual blocks to stack the LSTM network depth. The activation function was dynamically selected by global information encoding to reduce the number of parameters during enhancing the computational power of network. The model fitting capability was improved by dynamically adjusting the number of layers of residual connections to the input through attention mechanism. The residual network and Dynamic ReLU activation function were given, and the overall framework of LSTM named entity recognition was established based on hierarchical residual connections. The residual connection module, the Dynamic ReLU module and the attention mechanism module were defined. The proposed method was compared with related algorithms of FLAT and Lattice LSTM, and the experiments were conducted on Weibo and Resume dataset. The results show that the LSTM based on hierarchical residual connectivity achieves the best effect on the Weibo corpus and is second only to FLAT on the Resume corpus with F1 of 0. 700 1 and 0. 958 6, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Taiwan Journal of Linguistics is the property of Graduate Institute of Linguistics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Taiwan Journal of Linguistics is the property of Graduate Institute of Linguistics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Geography & Geographic Information Science is the property of Geography & Geo-Information Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, deep learning has made a breakthrough in the field of speech recognition, and pushes forward the wide application of speech recognition technology in people's daily lives. Further optimization of the speech recognition model needs to be supported by a larger scale calibrated data. However, the scale of the current open source audio data set is still too small, and corpus is mostly written language of news-based long texts. This paper, by talking about the popular speech recognition applications like human-computer interaction and intelligent customer service, builds and opens the largest ever Chinese Mandarin speech corpus DTZH1505 through crowdsourcing. Data set records natural speech of 6 408 speakers from 8 major Chinese dialect regions and 33 provinces, up to 1 505 hours and on various scenes like social networking, human-computer interaction, intelligent customer service and on-board commands. It can be widely used in the researches of corpus linguistics, conversation analysis, speech recognition, as well as speaker recognition. This paper implements a series benchmark speech recognition experiments, and the results show that: compared to the same scale Chinese speech corpus aishell2, the speech recognition model based on this data set has better performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, the word “油腻（Youni）” has derived a series of new semantics in the network context and has been widely used in written expressions. However, the existing research and the interpretation of modern Chinese dictionaries have insufficient understanding of its semantics. Based on BCC corpus and CCL corpus, the authors investigate the semantic system of “油腻（Youni）” and try to clarify the performance characteristics and popular motivation of its semantic derivation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Based on the study of the sentence pattern of “差一点没 VP”, the author extracts the relevant corpus of “差一点” from large-scale corpus and investigates the subtle differences of the meanings of the synonyms in Chinese and English. it is found that, with “差一点（chayidian）” as the core, there is a hierarchical sequence of “差一点（chayidian）”,“险些（xianxie）”,“几乎（jihu）” and “差不多（chabuduo）”. In English, the different translation methods of the word are first clarified, and then the syntactic and semantic characteristics of each pair of translation methods are distinguished. [ABSTRACT FROM AUTHOR]

Aiming at the problem of increasingly rich multilingual texts and lack of large-scale labeled parallel corpora on the Internet, in order to mine the relevance between languages from multilingual information sources and expand the knowledge map, this paper proposed a cross language relations hip extraction method based on attention transfer. Firstly, according to the actual parallel corpus between languages, it classified the cross language parallel corpus mapping, and for the low resource language pairs lacking seed dictionaries, it proposed a neural network translation model to obtain the target language data set and save the corresponding attention weight relationship between multiple languages, and then it extracted the entity relationship feature of training data by using BERT end-to-end joint extraction model. Finally, it used the reverse transferred attention to extract the enhanced relationship. Experiments show that the relationship extraction effect of this model is better than other models in accuracy and regression, and also shows better performance in the absence of bilingual dictionary. [ABSTRACT FROM AUTHOR]

Copyright of Chinese as a Second Language is the property of John Benjamins Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study proposes a corpus-based keyword network analysis method to explore topic frame of genetic modified food (GM food) news coverage of Taiwan from 2005 to 2020. Keywords were first extracted through keyword analysis, followed by construction of keyword network diagram through network analysis tool Gephi. Then, Gephi’s modularity and R language’s QAP analysis were applied to discern topic frames. The study found that the year of 2012 has marked a significant demarcation of GM food news topic frames. The discourse of GM food after 2012 has stabilized together with a lot description of possible harms caused by GM food. This research provides a new method for news topic frame analysis on the basis of corpus analysis. [ABSTRACT FROM AUTHOR]

To solve the problem of data distribution difference among different corpora, this paper proposed a cross-corpus speech emotion recognition algorithm based on subdomain adaptive deep autoencoder. Firstly, it used two depth autoencoders to obtain representative low-dimensional emotional features of source domain and target domain, respectively. Then, it used an adaptive sub-domain module based on LMMMD to achieve the alignment of feature distribution between source domain and target domain in different low-dimensional emotional category spaces. Finally, it used the tagged source domain data to supervise the training of the model. In the cross-corpus recognition scheme with eNTERFACE library as the source domain and Berlin library as the target domain, the accuracy of the proposed algorithm 5.26%～19.73% higher than that of other algorithms. In the cross-corpus recognition scheme with Berlin library as the source domain and eNTERFACE library as the target domain, the accuracy of the proposed algorithm is 7.34%～8.18% higher than that of other algorithms. Therefore, the proposed method can effectively extract the common sentiment features of different corpora and improve the performance of cross-corpus speech sentiment recognition. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

During the model training, training corpora usually contains a lot of external problem-specific information that cannot be used by the model directly. Due to the flexibility and simplicity of its framework, Posterior regularization has been widely applied in the fields of natural language processing and sample selection of classification tasks. The aim of the posteriori regularization framework is to limit the capacity of the model posteriori on unmarked data, thus guiding the model to learn and achieve the desired performance. Firstly, this paper systematically described the problem of PR. Then it introduced the three general frameworks of PR, pointed the motivation of every PR and the specific form of every PR model, and the advantages of every PR model, the problems that every PR model could solve and the typical application scenarios that PR could be used. Lastly, this paper pointed out the research directions of the posterior regularization models in the future and summarized the content of the total paper. [ABSTRACT FROM AUTHOR]

The sense distribution of"亮(liang) "in modern Chinese was analyzed with a corpus of 10000 entries. It is found that,besides the existing seven meanings,there are other four meanings including light emitted by aluminous object,superior in status or quality to those of the same kind,bright future and bright and excited sight.The causes of the new senses are analyzed with qualia structure theory. [ABSTRACT FROM AUTHOR]

Recently, with the emergence and popularity of intelligent applications, non-task oriented dialogue system has played an increasingly important role in daily life . Generation-based dialogue systems receive extraordinary attention of some researchers because they a re more flexible. In order to improve the flu ency and contextual relevance of the responses generated by models, this paper proposed an open domain dialogue gene ration model based on binary discriminator in terms of a multi-view adversarial learning framework. The generator of the model rewrote a retrieved response to get a generated response . While the discriminator was composed of two binary classifiers and distinguished the human-generated responses from machine generated ones. Experiments on a Chinese dialogue corpus sh ow that the model has higher scores on both human and automatic evaluation than baselines. Experiments also show that multi-view training with binary discriminators can improve both the fluency and contextual relevance of the generated responses. [ABSTRACT FROM AUTHOR]

Based on the NT clause theory, this paper carried out the NT clause identification task of punctuation sentences and explored the application effect of the language model in this task. Furthermore, it divided this task into single NT clause identification and sequential NT clauses identification task. In the single NT clause identification task, this paper formalized it into a machine reading comprehension task. From the results, it obtained the accuracy rate of 83 . 46% on the Fortress Besieged corpus, and reached the accuracy rate of 91. 21 % in the fish encyclopedia corpus. In the sequential NT clauses identification task, using the single NT model, it fed the punctuation sentences sequence in a pipe lined manner and got the sequential NT clauses. The accuracy rate in fish encyclopedia corpus reached 82. 03% . The experimental results show that the proposed method can effectively improve the accuracy of Chinese NT clause identification. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Training text simplification model based on seq2seq requires large-scale parallel corpora. However, current task lacks large-scale and well-labeled parallel corpora. To address the above issues, this paper proposed an unsupervised text simplification algorithm that made the learning of the model only need simple and complex sentence datasets without labels. First, the method used denoising autoencoder to learn from simple sentence corpus and complex sentence corpus, respectively, to obtain a simple sentence autoencoder and a complex sentence autoencoder. Then, it combined the two autoencoders to form an initial text simplification model and a text complication model. Finally, it used back-translation to convert the unsupervised text simplification problem into a supervised problem, and iteratively optimized the text simplification model. Experiments on the standard dataset show that the method is superior to the existing unsupervised model on the general indicators BLEU and SARI, and the model has simplified effects at both the lexical and syntactic level. [ABSTRACT FROM AUTHOR]

Currently, in reconstruction of normal speech from whispered speech based on neural network, the spectral envelope of the whisper is often used to estimate F0 characteristics of the normal speech. Such algorithms have certain deficiencies in the accuracy of F0. There is a clear lack of naturalnes, and sometimes the pitch distortion occurs. This paper proposes a method for predicting the F0 of normal speech frame by frame using the Bi-long short-term memory (BLSTM) deep network with the acoustic fusion feature of normal speech. Firstly, the STRAIGHT model and related codes are used to preprocess the whisper and the normal speech corpus. Respectively, extract the Mel-scale frequency cepstral coefficient (MFCC), rhythm and spectral envelope of the whisper speech and the F0 and spectral envelope of the normal speech. Secondly, the BLSTM deep network is used to establish a mapping relationship between spectrums of whisper and normal speech, and a mapping relationship between MFCC, rhythm and spectral envelope features of whisper speech and F0 of normal speech. Finally, according to MFCC, rhythm and spectral envelope features of whisper speech, the F0 and spectral envelope of the corresponding normal speech are obtained, and the normal speech is synthesized using the STRAIGHT model. The experimental results show that compared with the estimation of the F0 using only the spectral envelope, the introduction of fusion features of phonetic rhythm and MFCC is a good complement to the F0 features, which solves the phenomenon of pitch disorders and the converted speech is closer to normal speech in rhythm. [ABSTRACT FROM AUTHOR]

Guan Yingmings’ Research on Apology Speech Act in Modern Chinese, with the systematicness, innovativeness, scientific method and rich corpus, reflects the authors’ solid style of study. It is an academic work with both theoretical and practical significance in the field of apology speech act of in recent years. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Event extraction is an important and challenging task in NLP, completing the identification of event triggers and their arguments from the text. For multiple-event extraction tasks with multiple events in a sentence, this paper proposed a model based on a variant of attention mechanism called DyMAN, which could capture richer context representation and keep more valuable information than the normal attention. The experiments demonstrate that the proposed model can achieve stateof- the-art performance on the ACE 2005 corpus. Compared with the previous best model named JRNN, the DyMAN model achieved a 9. 8% improvement in trigger word classification tasks, and a 4. 5% improvement in factor classification tasks. [ABSTRACT FROM AUTHOR]

In order to get valuable information in bilateral cooperation in real time, it is of utmost importance to efficiently extract international cooperation elements in Web diplomacy news. This paper abstracted the international cooperation element extraction into a problem similar to named entity recognition. First of all, it defined the connotations of international cooperation elements. Secondly, it extracted the rules that contained domain knowledge. Then it proposed a method of extracting international cooperation elements for diplomatic news texts combined with neural network and domain knowledge. Finally, this paper compared the proposed method with the neural network and its own rule combination in the same corpus. The experimental results show that the proposed method has better results. [ABSTRACT FROM AUTHOR]

The method of Chinese existing automatic text summarization mainly utilizes the text's own information, and its defect is that it cannot make full use of the related semantic information between the words. Therefore, this paper proposed an improved Chinese text summarization method. This method integrated the information of the external corpora into the TextRank algorithm in the form of a word vector. Combined TextRank with word2vec, it mapped each word in the sentence to the high dimensional lexicon to form a sentence vector. This method fully considered the similarity between sentences, the coverage of keywords and the similarity between sentence and title to calculate the influence weights among sentences, and choose the top-ranked sentences used as the summarization of the text. The results of experiment show that this method achieves good results in the data set of this paper, and is more effective than the original method in extracting Chinese summarization automatically. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin University of Science & Technology is the property of Journal of Harbin University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to cope with the problem of data sparsity and curse of dimensionality in text classification, this paper proposed a short text classification framework by taking keyword as features and assigning keyword similarity as feature weight. First, it trained a word2vec model with large corpus data, then got keywords of each category text by textrank. And it selected unique keywords from the keywords collection as features. For each feature, it calculated the similarity of words in the short text by word2vec model, and assigned the maximum similarity as the weight of the feature. Finally, it chose KNN and SVM as classifier. Experiments on dataset of Chinese news headlines demonstrate that the accuracy outperforms other usual methods by 6%. [ABSTRACT FROM AUTHOR]

Due to the lack of systematic research on the feature expression of Uyghur text sentiment classification, this paper used the traditional n-gram features as the basis to extract new features and combined features from Uyghur sentiment corpora on different scales, and used support vector machine(SVM) classifier to classify the corpora as positive and negative. Results indicated that, in the Uyghur text sentiment classification, the unigram features in the basic features have the best classification efficiency. The combination of unigram features and phrase features can further improve the classification efficiency. The best performance of the combined features, the classification accuracy is 1.78% higher than that of unigram. This paper first made a comprehensive evaluation of the classification performance of different features on a unified data set. The research results can be applied as a reference for future Uyghur sentiment classification research. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Physical Education Institute / Shanghai Tiyu Xueyuan Xuebao is the property of Shanghai Physical Education Institute and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)