检索结果-南通市图书馆

Predicting Chinese Abbreviations from Definitions:An Empirical Learning Approach Using Support Vector Regression

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2008年第4期23卷 602-611页

作者：孙栩王厚峰王波 Institute of computational linguistics School of Electronics Engineering and Computer Science

In Chinese, phrases and named entities play a central role in information retrieval. Abbreviations, however make keyword-based approaches less effective. This paper presents an empirical learning approach to Chinese abbreviation prediction. In this study, each abbreviation is taken as a reduced form of the corresponding definition （expanded form）, and the abbreviation prediction is formalized as a scoring and ranking problem among abbreviation candidates, which are automatically generated from the corresponding definition. By employing Support Vector Regression （SVR） for scoring, we can obtain multiple abbreviation candidates together with their SVR values, which are used for candidate ranking. Experimental results show that the SVR method performs better than the popular heuristic rule of abbreviation prediction. In addition, in abbreviation prediction, the SVR method outperforms the hidden Markov model （HMM）.

关键词： statistical natural language processing abbreviation prediction support vector regression word clustering

Using an improved sentence paradigm of event-related potentials to examine puns' cognitive mechanism

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2021年第3期28卷 102-110页

作者： Yang Siqin Jiang Minghu laboratory of computational linguistics Tsinghua UniversityBeijing 100084China School of Humanities Tsinghua UniversityBeijing 100084China

In order to specify brain temporal dynamics difference between two representative puns, homonymic and semantic puns, alternate presentation of words and phrase(APWP) paradigm was proposed. The highlight of APWP paradigm is to make sentences strictly presented in word-phrase-word-phrase-word forms, which helps relieve visual fatigue of the monotonous presentation form and prevent disturbance by the settled position of the ending word. Following the APWP paradigm, participants are invited to read puns presenting in word-phrase-word-phrase-word forms. Meanwhile, event-related potential(ERP) was adopted to record their electroencephalogram(EEG) data. By observing two linguistic cognitive indexes of EEG data, N400 and P600 caused by puns, it was found that there were significant difference of logical mechanisms between homonymic and semantic puns. For homonymic puns, a significant P600 effect without any obvious N400 amplitude was elicited for the pronunciation of heterograph. For semantic puns, an apparent N400 amplitude might reflect ambiguities and comprehensive difficulty of a homonym into its discourse context. This study also conveyed that the APWP paradigm proved to be a good model for sentences research, which can be applied to other linguistic phenomena of complete context, such as metaphor, irony and jokes, sentence pattern and syntactic research.

关键词： alternate presentation of words and phrase(APWP)paradigm cognitive processing puns event-related potential(ERP)

Pitch models of Mandarin text-to-speech

在线全文

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2009年第2期16卷 179-184页

作者：邵艳秋穗志方韩纪庆 Institute of computational linguistics Peking University School of Computer Science and Technology Harbin Institute of Technology

The function of prosody model will directly affect the naturalness of synthesized *** at the difficulty in generating the pitch contour in prosody model,two pitch models namely corpus-based pitch model and pitch pattern model are deeply studied in this *** problems in the corpus-based model are calculation of the distance and searching of the optimal path with dynamic programming *** the pitch pattern model,parameters such as pitch pattern,pitch average and pitch range are used to describe the pitch contour,and six pitch patterns are *** the generation of pitch contour,the pitch pattern model is more flexible than the corpus-based *** of the two models are linked to the real TTS system,and the MOS results of synthesized Mandarin speech show that the pitch pattern model is better than the corpus-based pitch model.

关键词： speech synthesis prosody model pitch model pitch pattern

Recent advances of neural text generation:Core tasks,datasets,models and challenges

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2020年第10期63卷 1990-2010页

作者： JIN HanQi CAO Yue WANG TianMing XING XinYu WAN XiaoJun Wangxuan Institute of Computer Technology Peking UniversityBeijing 100871China Center for Data Science Peking UniversityBeijing 100871China The MOE Key laboratory of computational linguistics Peking UniversityBeijing 100871China

In recent years,deep neural network has achieved great success in solving many natural language processing ***,substantial progress has been made on neural text generation,which takes the linguistic and non-linguistic input,and generates natural language *** survey aims to provide an up-to-date synthesis of core tasks in neural text generation and the architectures adopted to handle these tasks,and draw attention to the challenges in neural text *** first outline the mainstream neural text generation frameworks,and then introduce datasets,advanced models and challenges of four core text generation tasks in detail,including AMR-to-text generation,data-to-text generation,and two text-to-text generation tasks(i.e.,text summarization and paraphrase generation).Finally,we present future research directions for neural text *** survey can be used as a guide and reference for researchers and practitioners in this area.

关键词： natural language generation neural text generation AMR-to-text data-to-text text summarization paraphrase generation

Discrimination of Chinese Quantitative Style Features Based on Text Clustering 11th

在线全文

学校读者我要写书评

暂无评论

Discrimination of Chinese Quantitative Style Features Based ...

The Pragmatics Information Extraction Based on BP Neural Network 11th

2012 IEEE 11th International Conference on Signal Processing(ICSP 2012)

作者： Hou Renkui Jiang Minghu Lab. of computational linguistics School of Humanities and Social SciencesTsinghua University

ISBN: (纸本)9781467321969

The styles of "News Broadcast" and "Qiang Qiang Conversation between Three Individuals" are different. The former is broadcasting, while the latter is conversational. This paper collects the corpus of both programs and selects sentence length, word length and sentence-initial word POS as the characters to generate the text vectors. And the texts are clustered by the Euclidean distance and ward algorithm. The analysis showed that the sentence length, word length and sentence-initial word POS can be used as Chinese quantitative stylistic characters.

关键词： Text Clustering type of writing sentence length word length sentence-initial word POS

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

The Pragmatics Information Extraction Based on BP Neural Net...

Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs

2012 IEEE 11th International Conference on Signal Processing(ICSP 2012)

作者： Liu Ding Jiang Minghu School of Humanities and Social Sciences Lab.of Computational LinguisticsTsinghua University

ISBN: (纸本)9781467321969

This article describes a method that uses the BP neural network to extract the pragmatics information from the conversational corpus. Then cluster the texts based on the pragmatics information matrix that generated by the BP neural network. And, compare with the original term-document matrix, the pragmatics information matrix improve the clustering results obviously.

关键词： BP neural network pragmatics conversational corpus text clustering

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Data Intelligence 2022年第1期4卷 20-40页

作者： Zhibin Chen Yuting Wu Yansong Feng Dongyan Zhao Wangxuan Institute of Computer Technology Peking UniversityBeijing 100871China Center for Data Science Peking UniversityBeijing 100871China The MOE Key laboratory of computational linguistics Peking UniversityBeijing 100871China

Entity Linking(EL)aims to automatically link the mentions in unstructured documents to corresponding entities in a knowledge base(KB),which has recently been dominated by global *** many global EL methods attempt to model the topical coherence among all linked entities,most of them failed in exploiting the correlations among manifold knowledge helpful for linking,such as the semantics of mentions and their candidates,the neighborhood information of candidate entities in KB and the fine-grained type information of *** we will show in the paper,interactions among these types of information are very useful for better characterizing the topic features of entities and more accurately estimating the topical coherence among all the referred entities within the same *** this paper,we present a novel HEterogeneous Graph-based Entity Linker(HEGEL)for global entity linking,which builds an informative heterogeneous graph for every document to collect various linking *** HEGEL utilizes a novel heterogeneous graph neural network(HGNN)to integrate the different types of manifold information and model the interactions among *** on the standard benchmark datasets demonstrate that HEGEL can well capture the global coherence and outperforms the prior state-of-the-art EL methods.

关键词： Entity linking Heterogeneous graph Graph neural network Entity disambiguation Knowledge base

Semantic Computation in a Chinese Question—Answering System

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2002年第6期17卷 933-939页

作者：李素建张健黄雄白硕刘群 Institute of computational linguistics Peking University Beijing 100871 P.R. China Software Department Institute of Computing Technology The Chinese Academy of Sciences Beijing 100080 P.R. China

This paper introduces a kind of semantic computation and presents how tocombine it into our Chinese Question-Answering (QA) system. Based on two kinds of languageresources, Hownet and Cilin, we present an approach to computing the similarity and relevancybetween words. Using these results, we can calculate the relevancy between two sentences andthen get the optimal answer for the query in the system. The calculation adopts quantitativemethods and can be incorporated into QA systems easily, avoiding some difficulties in conven-tional NLP (Natural Language Processing) problems. The experiments show that the resultsare satisfactory.

关键词： similarity relevancy Hownet question-answering natural language processing

A Combined Weight method in Automatic Classification of Chinese Text

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Combined Weight method in Automatic Classification of Chin...