检索结果-南通市图书馆

Combining Trigram and Automatic Weight Distribution in Chinese Spelling Error Correction

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 2002年第6期17卷 915-923页

作者：李建华王晓龙 School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001P.R.China

The researches on spelling correction aiming at detecting errors in texts tendto focus on context-sensitive spelling error correction, which is more difficult than traditionalisolated-word error correction. A novel and efficient algorithm for the system of Chinese spellingerror correction, CInsunSpell, is presented. In this system, the work of correction includes twoparts: checking phase and correcting phase. At the first phase, a Trigram algorithm within onefixed-size window is designed to locate potential errors in local area. The second phase employsa new method of automatically and dynamically distributing weights among the characters inthe confusion set as well as in the Bayesian language model. The tactics used above exhibitsgood performances.

关键词： spelling error correction language model edit distance weight distribution

Protein Structure Prediction:Challenges,Advances,and the Shift of Research Paradigms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2023年第5期21卷 913-925页

作者： Bin Huang Lupeng Kong Chao Wang Fusong Ju Qi Zhang Jianwei Zhu Tiansu Gong Haicang Zhang Chungong Yu Wei-Mou Zheng Dongbo Bu Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Changping Laboratory Beijing 102206China Microsoft Research AI4Science Beijing 100080China Huawei Noah’s Ark Lab Wuhan 430206China Zhongke Big Data Academy Zhengzhou 450046China Institute of Theoretical Physics Chinese Academy of SciencesBeijing 100190China

Protein structure prediction is an interdisciplinary research topic that has attracted researchers from multiple fields,including biochemistry,medicine,physics,mathematics,and computer *** researchers adopt various research paradigms to attack the same structure prediction problem:biochemists and physicists attempt to reveal the principles governing protein folding;mathematicians,especially statisticians,usually start from assuming a probability distribution of protein structures given a target sequence and then find the most likely structure,while computer scientists formulate protein structure prediction as an optimization problem-finding the structural conformation with the lowest energy or minimizing the difference between predicted structure and native *** research paradigms fall into the two statistical modeling cultures proposed by Leo Breiman,namely,data modeling and algorithmic ***,we have also witnessed the great success of deep learning in protein structure *** this review,we present a survey of the efforts for protein structure *** compare the research paradigms adopted by researchers from different fields,with an emphasis on the shift of research paradigms in the era of deep *** short,the algorithmic modeling techniques,especially deep neural networks,have considerably improved the accuracy of protein structure prediction;however,theories interpreting the neural networks and knowledge on protein folding are still highly desired.

关键词： Protein folding Protein structure prediction Deep learning Transformer language model

PERFORMANCE COMPARISON OF language modelS FOR INFORMATION RETRIEVAL

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

PERFORMANCE COMPARISON OF LANGUAGE MODELS FOR INFORMATION RE...

Short Texts Classification Through Reference Document Expansion

IFIP TC12 WG12.5-Second IFIP Conference on Artificial Intelligence Applications and Innovations(AIAI2005)

作者： Shuaixiang Dai Qian Diao Changle Zhou Department of Computer Science and Technology Xiamen University Intel China Research Center

Vector Space model（VSM）,Statistical language model（SLM） and Inference Network are three distinguished language *** of evaluating their performance directly,we estimate the information strategies founded on them using the known measures:precision and ***’s more,we proposed the Sort Order Rationality（SOR） to make further performance comparison among different language *** models are tested on a standard testing *** important conclusions are attained:（1）.The IR model combining the statistical language modeling and inference network approaches is better than that only founded on statistical language modeling ***’s more,it is also better than that based on vector space modeling approach.（2）.The performance of IR model based on VSM is similar to that based on SLM.（3）.The Dirichlet priors method often is a better option to smooth a statistical language *** some respects,these conclusions provide some experimental bases for constructing an efficient information retrieval system.

关键词： language model language modeling approach information retrieval

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

Chinese Journal of Electronics 2014年第2期23卷 315-321页

作者： YANG Zhen FAN Kefeng LAI Yingxu GAO Kaiming WANG Yong College of Computer Science Beijing University of Technology China Electronics Standardization Institute CSIP Guangxi Section Guilin University of Electronic Technology

With the rapid development of information technology, short texts arising from socialized human interaction are gradually predominant in network information streams. Accelerating demands are requiring the industry to provide more effective classification of the brief ***, faced with short text documents, each of which contains only a few words, traditional document classification models run into difficulty. Aggressive documents expansion works remarkably well for many cases but suffers from the assumption of independent, identically distributed observations. We formalize a view of classification using Bayesian decision theory, treat each short text as observations from a probabilistic model, called a statistical language model, and encode classification preferences with a loss function defined by the language models and the external reference document. According to Vapnik’s methods of Structural risk minimization(SRM), the optimal classification action is the one that minimizes the structural risk, which provides a result that allows one to trade off errors on the training sample against improved generalization performance. We conduct experiments by using several corpora of microblog-like data, and analyze the experimental results. With respect to established baselines,results of these experiments show that applying our proposed document expansion method produces better chance to achieve the improved classification performance.

关键词： Text classification Short texts language model Document expansion External reference

Relation Extraction Based on Prompt Information and Feature Reuse

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Data Intelligence 2023年第3期5卷 824-840页

作者： Ping Feng Xin Zhang Jian Zhao Yingying Wang Biao Huang Jilin University Changchun Jilin 130012China Changchun Universiy Changchun Jilin 130022China Jilin Provincial Key Laboratory of Human Health State Identification and Function Enhancement Changchun Jjilin 130022China

To alleviate the problem of under-utilization features of sentence-level relation extraction,which leads to insufficient performance of the pre-trained language model and underutilization of the feature vector,a sentence-level relation extraction method based on adding prompt information and feature reuse is *** first,in addition to the pair of nominals and sentence information,a piece of prompt information is added,and the overall feature information consists of sentence information,entity pair information,and prompt information,and then the features are encoded by the pre-trained language model ***,in the pre-trained language model,BIGRU is also introduced in the composition of the neural network to extract information,and the feature information is passed through the neural network to form several sets of feature *** that,these feature vectors are reused in different combinations to form multiple outputs,and the outputs are aggregated using ensemble-learning soft voting to perform relation *** addition to this,the sum of cross-entropy,KL divergence,and negative log-likelihood loss is used as the final loss function in this *** the comparison experiments,the model based on adding prompt information and feature reuse achieved higher results of the SemEval-2010 task 8 relational dataset.

关键词： relation extraction language model prompt information feature reuse loss function

Roman to Gurmukhi Social Media Text Normalization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2020年第4期13卷 407-435页

作者： Jagroop Kaur Jaswinder Singh Department of Computer Science and Engineering Punjabi UniversityPatialaIndia

Purpose-Normalization is an important step in all the natural language processing applications that are handling social media *** text from social media poses a different kind of problems that are not present in regular ***,a considerable amount of work has been done in this direction,but mostly in the English *** who do not speak English code mixed the text with their native language and posted text on social media using the Roman *** kind of text further aggravates the problem of *** paper aims to discuss the concept of normalization with respect to code-mixed social media text,and a model has been proposed to normalize such ***/methodology/approach-The system is divided into two phases-candidate generation and most probable sentence *** generation task is treated as machine translation task where the Roman text is treated as source language and Gurmukhi text is treated as the target *** translation system has been proposed to generate candidate *** candidates are generated,the second phase uses the beam search method for selecting the most probable sentence based on hidden Markov ***-Character error rate(CER)and bilingual evaluation understudy(BLEU)score are *** proposed system has been compared with Akhar software and RB\_R2G system,which are also capable of transliterating Roman text to *** performance of the system outperforms Akhar *** CER and BLEU scores are 0.268121 and 0.6807939,respectively,for ill-formed *** limitations/implications-It was observed that the system produces dialectical variations of a word or the word with minor errors like diacritic *** checker can improve the output of the system by correcting these minor *** experimentation is needed for optimizing language identifier,which will further help in improving the *** language model also seeks further ***

关键词： Social media text Text normalization Code-mixed text Deep neural network language model

Querying Linked Data Based on Hierarchical Multi-Hop Ranking model

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 Shanghai Jiaotong university(Science) 2018年第4期23卷 568-576页

作者： LI Junxian WANG Wei WANG dingjing School of Computer Jiangsu University of Science and Technology Zhenjiang 212003 Jiangsu China School of Computer Science Fudan University Shanghai 200433 China Yangzhou Polytechnic College Yangzhou 225009 Jiangsu China

How to query Linked Data effectively is a challenge due to its heterogeneous *** are three types of heterogeneities,i.e.,different structures representing entities,different predicates with the same meaning and different literal formats used in *** based on ontology mapping or Information Retrieval(IR) cannot deal with all types of *** these limitations,we propose a hierarchical multi-hop language model(HMPM).It discriminates among three types of predicates,descriptive predicates,out-associated predicates and in-associated predicates,and generates multi-hop models for them *** predicates' similarities between the query and entity are organized into a hierarchy,with predicate types on the first level and predicates of this type on the second *** candidates are ranked in ascending *** evaluated HMPM in three datasets,DBpedia,Linked MDB and *** results of experiments show that the effectiveness and generality of HMPM outperform the existing approaches.

关键词： hierarchical multi-hop ranking model(HMPM) Linked Data language model

A new approach to query expansion in information retrieval

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2008年第1期14卷 77-80页

作者：李卫疆 Zhao Tiejun Wang Xian＇gang MOE-MS Key Laboratory of Natural language Processing and Speech -School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 P.R. China

To eliminate the mismatch between words of relevant documents and user's query and more seriousnegative effects it has on the performance of information retrieval,a method of query expansion on the ba-sis of new terms co-occurrence representation was put forward by analyzing the process of *** expansion terms were selected according to their correlation to the whole *** the sametime,the position information between terms were *** experimental result on test retrievalconference(TREC)data collection shows that the method proposed in the paper has made an improve-ment of 5%～19% all the time than the language modeling method without *** to thepopular approach of query expansion,pseudo feedback,the precision of the proposed method is competi-tive.

关键词： information retrieval language model query expansion

Evaluation on ChatGPT for Chinese language Understanding

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Data Intelligence 2023年第4期5卷 885-903页

作者： Linhan Li Huaping Zhang Chunjin Li Haowen You Wenyao Cui School of Computer Science Beijing Institute of TechnologyBeijingChina

ChatGPT has attracted extension attention of academia and *** paper aims to evaluate ChatGPT in Chinese language understanding capability on 6 tasks using 11 *** indicate that ChatGPT achieved competitive results in sentiment analysis,summary,and reading comprehension in Chinese,while it is prone to factual errors in closed-book ***,on two more difficult Chinese understanding tasks,that is,idiom fill-in-the-blank and cants understanding,we found that a simple chain-of-thought prompt can improve the accuracy of ChatGPT in complex *** paper further analyses the possible risks of using ChatGPT based on the ***,we briefly describe the research and development progress of our ChatBIT.

关键词： language model ChatGPT ChatBIT Chinese language Understanding Artificial intelligence