检索结果-内蒙古大学图书馆

13th International Conference on Mobile Ad-hoc and Sensor Networks, MSN 2017

作者： Latif, Zohaib Sharif, Kashif Alvi, Maria K. Li, Fan School of Computer Science Beijing Institute of Technology Beijing China Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan

ISBN: (纸本)9789811088896

The amount of research done in the field of mobile ad hoc networks is extraordinarily large. Evaluation of protocols designed for ad hoc networks is challenging as the cost of node deployment in terms of resources required is high, hence, most of the researchers use simulations for performance evaluation. In this paper we address the pitfalls of simulation studies in ad hoc routing protocols published in recent years. We have conducted a survey to evaluate the current state of simulation studies published in top conference/journals of the communication domain. In majority of the published papers (the way simulation results are reported) we have found design flaws, unrealistic assumptions, are non-reproducible, and statistically invalid results. We also propose a standardizing architecture for automating the reporting and replication process for network simulators. This platform independent architecture alleviates the challenge of simulation parameter reporting and facilitates in designing better network simulation experiments. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Denoising Method for Distant Supervised Relation Extraction Based on Deep Clustering

A Denoising Method for Distant Supervised Relation Extractio...

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Li, Hongao Sun, Xin Yang, Kaige Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Southeast Academy of Information Technology Fujian Putian351100 China

ISBN: (纸本)9789811694912

Distant supervision for relation extraction uses an external knowledge base as supervision signals to automatically label corpus and has attracted more and more attention. However, this method has an ideal hypothesis that all instances containing the same entity pairs represent the same relation, which will lead to a lot of noisy data and affect the training effect of classifier. Aiming at the noise problem of distant supervised dataset, we propose a denoising method based on deep clustering. First, the deep clustering method is used to train the text features and clustering centers, and the effect of clustering is improved by using the information of mask entity pairs. Then high quality training samples are obtained by removing the noisy data, so as to achieve the effect of denoising. Experimental results show that the proposed model can effectively improve the performance of relation extraction by comparing with the traditional denoising methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

A NEW ALGORITHM OF EXTRACTING MAXIMAL-LENGTH EVALUATION PHRASE AND COLLOCATION OF EVALUATION

A NEW ALGORITHM OF EXTRACTING MAXIMAL-LENGTH EVALUATION PHRA...

引用

2012 IEEE 2nd International Conference on cloud computing and Intelligence Systems

作者： Quanchao Liu Heyan Huang Changzhi Wang Chong Feng Beijing Engineering Applications Research Center of High Volume Language Information Processing and Cloud Computing Beijing Institute of Technology

We propose an algorithm of automatically identifying maximal-length evaluation (MEP) based on statistics and rules. The principle of the algorithm is that transform the problem of evaluation phrase recognition into a sequence tagging problem, use conditional random fields model for recognizing simple structure phrase of evaluation, and then automatically identify MEP with complex structure based on the establishment and application of the rule base. The testing precision and recall rate reached 72.38%. Based on the work above, we proposed a new algorithm of automatically extracting collocation of evaluation based on rules and make the automatic extraction of evaluation object and the MEP become reality. Experiment was conducted at Netease car portal for test, and got a higher accuracy rate.

关键词： Maximal-length evaluation phrase Conditional random fields Sentiment evaluation unit Collocation of evaluation Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Capturing Global Structural information in Long Document Question Answering with Compressive Graph Selector Network

Capturing Global Structural Information in Long Document Que...

引用

2022 Conference on Empirical Methods in Natural language processing, EMNLP 2022

作者： Nie, Yuxiang Huang, Heyan Wei, Wei Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Beijing Institute of Technology Southeast Academy of Information Technology China Huazhong University of Science and Technology China

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents. However, these methods usually ignore the global structure of the long document, which is essential for long-range understanding. To tackle this problem, we propose Compressive Graph Selector Network (CGSN) to capture the global structure in a compressive and iterative manner. The proposed model mainly focuses on the evidence selection phase of long document question answering. Specifically, it consists of three modules: local graph network, global graph network and evidence memory network. Firstly, the local graph network builds the graph structure of the chunked segment in token, sentence, paragraph and segment levels to capture the short-term dependency of the text. Secondly, the global graph network selectively receives the information of each level from the local graph, compresses them into the global graph nodes and applies graph attention to the global graph nodes to build the long-range reasoning over the entire text in an iterative way. Thirdly, the evidence memory network is designed to alleviate the redundancy problem in the evidence selection by saving the selected result in the previous steps. Extensive experiments show that the proposed model outperforms previous methods on two datasets. © 2022 Association for Computational Linguistics.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

System Report for CCL23-Eval Task 9: Improving MRC Robustness with Overlapping Segments Generation for GCRC advRobust 22

System Report for CCL23-Eval Task 9: Improving MRC Robustnes...

引用

22nd Chinese National Conference on Computational Linguistics, CCL 2023

作者： He, Suzhe Yang, Chongsheng Shi, Shumin Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

ISBN: (纸本)9781713889908

There are many challenges in machine reading comprehension when it comes to extracting semantically complete evidence for specific statement. Existing works on unsupervised evidence extraction can be mainly divided into two categories. The first category utilizes static word vectors and employs beam search iteratively to extract relevant sentences. The second category uses instance-level supervised methods, including independent evidence extraction and end-to-end evidence extraction. The former category involves a more complex process, while the latter category suffers from instability during joint training, which directly affects the stable improvement of model performance. In Task 9 of CCL23-Eval, this paper proposes an adaptive end-to-end evidence extraction method based on overlapping segments generation. This method addresses the uncertainty in evidence sentence boundaries by dividing the document into multiple overlapping sentence segments and extracting key parts as evidence to achieve overall semantic extraction. Simultaneously, the evidence extraction embedding module is optimized to achieve automatic adjustment of evidence segment confidence. Experimental results demonstrate that the proposed method greatly eliminates interference from redundant content, and with just one hyperparameter, it can stably improve the performance of the reading comprehension model, improving model robustness. © 2023 China National Conference on Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A parallel recurrent neural network for language modeling with POS tags 31

A parallel recurrent neural network for language modeling wi...

引用

31st Pacific Asia Conference on language, information and Computation, PACLIC 2017

作者： Su, Chao Huang, Heyan Shi, Shumin Guo, Yuhang Wu, Hao School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing100081 China Beijing Advanced Innovation Center for Imaging Technology Capital Normal University Beijing100048 China

language models have been used in many natural language processing applications. In recent years, the recurrent neural network based language models have defeated the conventional n-gram based techniques. However, it is difficult for neural network architectures to use linguistic annotations. We try to incorporate part-of-speech features in recurrent neural network language model, and use them to predict the next word. Specifically, we proposed a parallel structure which contains two recurrent neural networks, one for word sequence modeling and another for part-of-speech sequence modeling. The state of part-of-speech network helped improve the word sequence's prediction. Experiments show that the proposed method performs better than the traditional recurrent network on perplexity and is better at reranking machine translation outputs. Copyright © 2017 Chao Su, Heyan Huang, Shumin Shi, Yuhang Guo and Hao Wu

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Domain Assignment BaseC on Word-Gloss

引用

China Communications 2012年第3期9卷 19-27页

作者：朱朝勇黄河燕史树敏 School of Computer Science and Technology University of Science and Technology of China School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing & Cloud Computing Applications Beijing Institute of Technology

This paper proposes a hierarchical word domain assignment algorithm to automatically build domain dictionaries from Machine-Readable Dictionary(MRD).The process for word domain assignment can be divided into three steps:1) Hierarchical structure constructing;2) Classifier training;3) Word domain *** with the traditional methods,the hierarchical word domain assignment algorithm enhances the accuracy of word domain assignment while reducing human efforts on collecting *** on WordNet 2.0 show that 62.53% of the first domain labels are matched with the WordNet Domains 3.0 by using gloss-based word domain assignment,and the performance can be further improved by utilizing the hierarchical relationships among the domain sets.

关键词： natural language processing domaindictionary hierarchical classification domain as-sigrmaent WordNet MRD

来源：评论

学校读者我要写书评

暂无评论

Approximating to the Real Translation Quality for Neural Machine Translation via Causal Motivated Methods

引用

ACM Transactions on Asian and Low-Resource language information processing 2023年第5期22卷 1-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Haidian District Beijing China

It is hard to evaluate translations objectively and accurately, which limits the applications of machine translation. In this article, we assume that the above phenomenon is caused by noise interference during translation evaluation, and we handle the problem through a perspective of causal inference. We assume that the observable translation score is affected by the unobservable true translation quality and some noise simultaneously. If there is a variable that is related to the noise and independent to the true translation quality, the related noise can be eliminated by removing the effect of that variable from the observed score. Based on the above causality hypothesis, this article studies the length bias problem of beam search for neural machine translation (NMT) and the input related noise problem of translation quality estimation (QE). For the NMT length bias problem, we conduct the experiments on four typical NMT tasks (Uyghur–Chinese, Chinese–English, English–German, and English–French) with different scales of datasets. Comparing with previous approaches, the proposed causal motivated method is model-agnostic and does not require supervised training. For QE tasks, we conduct the experiments on the WMT’20 submissions. Experimental results show that the denoised QE results gain better Pearson’s correlation scores with human assessed scores compared to the original submissions. Further analyses on the NMT and QE tasks also demonstrate the rationality of the empirical assumptions made on our methods.

关键词： Neural machine translation causal inference half-sibling regression quality estimation

来源：评论

学校读者我要写书评

暂无评论

Improving neural machine translation with sentence alignment learning

引用

Neurocomputing 2021年 420卷 15-26页

作者： Xuewen Shi Heyan Huang Ping Jian Yi-Kun Tang School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

Neural machine translation (NMT) optimized by maximum likelihood estimation (MLE) usually lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge from bilingual sentence alignment learning. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates. The discriminator is constructed by gated self-attention based sentence encoders and trained with an N -pair loss for better capturing lexical evidences from bilingual sentence pairs. Then we propose an adversarial training framework as well as a sentence alignment-aware decoding method for NMT to transfer the discriminator’s learned semantic knowledge to NMT models. We conduct our experiments on Chinese → English, Uyghur → Chinese and English → German translation tasks. Experimental results show that our proposed methods outperform baseline NMT models on all these three translation tasks. Further analysis also indicates the characteristics of our approaches and details the semantic knowledge that transfered from the discriminator to the NMT model.

关键词： Neural machine translation Sentence alignment Adversarial training

来源：评论

学校读者我要写书评

暂无评论

Automatic Verification of Data-centric Web Service Specifications

引用

IERI Procedia 2013年 4卷 93-98页

作者： Zhi Fang Lejian Liao Ruoyu Chen Beijing Engineering Research Centre of High Volume Language Information Processing & Cloud Computing Applications School of Computer Science Beijing Institute of TechnologyBeijing 100081 China

Amodel are proposed for modeling data-centric Web services which are powered by relational databases and interact with users according to logical formulas specifying input constraints, control-flow constraints and state/output/action rules. The Linear Temporal First-Order Logic (LTL-FO) formulas over inputs, states, outputs and actions are used to express the properties to be *** have proven that automatic verification of LTL-FO properties of data-centric Web services under input-bounded constraints is decidable by reducing Web services to data-centric Web applications. Thus, we can verify Web service specifications using existing verifier designed for Web applications.

关键词： Web Service Automatic Verification First-Order Linear Temporal Logic

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：