检索结果-内蒙古大学图书馆

IEEE International Conference on cloud computing and Intelligence Systems (CCIS)

作者： Dan Luo Shumin Shi Rihai Su Heyan Huang School of Computer Sciences and Technology Beijing Institute of Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

Neural Machine Translation (NMT) has achieved state-of-the-art performance depending on the availability of copious parallel corpora. However, for low-resource NMT task, the scarcity of training data will inevitably lead to poor translation performance. In order to relieve the dependence on scale of bilingual corpus and to cut down training time, we propose a novel data augmentation method named SMC under scarce condition that can Sample Monolingual Corpus containing difficult words only in back-translation process for Mongolian-Chinese (Mn-Ch) and English-Chinese (En-Ch) NMT. Inspired by work in curriculum learning, our approach takes into account the various difficulty-degree of the sample and the corresponding model capabilities. Experimental results show that our method improves translation quality respectively by up to 2.4 and 1.72 BLEU points over the baselines on En-Ch and Mn-Ch datasets while greatly reducing training time.

关键词： Training Data models Task analysis Training data information processing cloud computing Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Temporal enhanced sentence-level attention model for hashtag recommendation

引用

CAAI Transactions on Intelligence Technology 2018年第2期3卷 95-100页

作者： Jun Ma Chong Feng Ge Shi Xuewen Shi Heyang Huang Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications College of Computer Science Beijing Institute of Technology University 5 South Zhong Guan Cun Street of Haidian District Beijing People's Republic of China

Hashtags of microblogs can provide valuable information for many natural language processing tasks. How to recommend reliable hashtags automatically has attracted considerable attention. However, existing studies assumed that all the training corpus crawled from social networks are labelled correctly, while large sample statistics on real social media shows that there are 8.9% of microblogs with hashtags having wrong labels. The notable influence of noisy data to the classifier is ignored before. Meanwhile, recency also plays an important role in microblog hashtag, but the information is not used in the existing studies. Some temporal hashtags such as World Cup will ignite at a particular time, but at other times, the number of people talking about it will sharply decrease. To address the twofold shortcomings above, the authors propose an long short-term memory-based model, which uses temporal enhanced selective sentence-level attention to reduce the influence of wrong labelled microblogs to the classifier. Experimental results using a dataset of 1.7 million microblogs collected from SINA Weibo microblogs demonstrated that the proposed method could achieve significantly better performance than the state-of-the-art methods.

关键词：分类器数据集计算机技术智能技术

来源：评论

学校读者我要写书评

暂无评论

Sharing Pre-trained BERT Decoder for a Hybrid Summarization

Sharing Pre-trained BERT Decoder for a Hybrid Summarization

引用

第十八届中国计算语言学大会暨中国中文信息学会2019学术年会

作者： Ran Wei Heyan Huang Yang Gao School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing 100081China

ISBN: (纸本)9783030323806

Sentence selection and summary generation are two main steps to generate informative and readable ***,most previous works treat them as two separated *** this paper,we propose a novel extractive-and-abstractive hybrid framework for single document summarization task by jointly learning to select sentence and rewrite *** first selects sentences by an extractive decoder and then generate summary according to each selected sentence by an abstractive ***,we apply the BERT pre-trained model as document encoder,sharing the context representations to both *** on the CNN/DailyMail dataset show that the proposed framework outperforms both state-of-the-art extractive and abstractive models.

关键词： Text Summarization Extractive and Abstractive Pretrained Based

来源：评论

学校读者我要写书评

暂无评论

Deep Hashing with Attribute Guidance for Image Retrieval

引用

Journal of Physics: Conference Series 2020年第1期1576卷

作者： Yao Lu Heyan Huang Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Department of Computer Science and Technology Beijing Institute of technology

Similarity-preserving hashing is an important method to solve approximate nearest neighbour search problem for image retrieval. Lots of works have been proposed for supervised hashing and image category labels are utilized as supervised information. However, current works ignore a fact that images can be described by a set of attributes. Intuitively, images of different categories with close visual features can be separated by their attribute features because attributes keep more detailed information. In this paper, we propose a novel supervised deep hashing method with image attribute guidance. Specifically, hash codes are learnt through image visual features and guided by image attributes by maintaining pair wise similarities between images as well as the corresponding attribute descriptions. Extensive experimental results on two benchmark datasets show that our proposed method achieves better performance compared with the state of the art hashing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task-oriented word embedding for text classification 27

Task-oriented word embedding for text classification

引用

27th International Conference on Computational Linguistics, COLING 2018

作者： Liu, Qian Huang, Heyan Gao, Yang Wei, Xiaochi Tian, Yuxin Liu, Luyang Department of Computer Science Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Centre for Artificial Intelligence University of Technology Sydney Australia

ISBN: (纸本)9781948087506

Distributed word representation plays a pivotal role in various natural language processing tasks. In spite of its success, most existing methods only consider contextual information, which is suboptimal when used in various tasks due to a lack of task-specific features. The rational word embeddings should have the ability to capture both the semantic features and task-specific features of words. In this paper, we propose a task-oriented word embedding method and apply it to the text classification task. With the function-aware component, our method regularizes the distribution of words to enable the embedding space to have a clear classification boundary. We evaluate our method using five text classification datasets. The experiment results show that our method significantly outperforms the state-of-the-art methods. © 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

CrowdX: Enhancing automatic construction of indoor floorplan with opportunistic encounters

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2018年第4期2卷 1–21页

作者： Chen, Huijie Li, Fan Hei, Xiaojun Wang, Yu School of Computer Science Beijing Institute of Technology Beijing Engineering Research Center High Volume Language Information Processing and Cloud Computing Applications Beijing China School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Department of Computer Science University of North Carolina at Charlotte Charlotte United States

The lack of floorplan limits the spread of pervasive indoor location-based services. Existing crowdsourcing based approaches mostly rely on identifying, locating landmarks in the environment and utilizing the spatial relationship between the landmarks and traces for efficiently constructing fine-grained floorplan. However, these methods are always restricted by the sparse landmark distribution or may cause privacy leakage. In this paper, we propose CrowdX, a crowdsourcing system for accurate, low-cost indoor floorplan construction enhanced with opportunistic encounters among mobile users. The key insight is that the spatial relation (i.e., the displacement of each user and the distance between each other during the encounter) will be extracted from the audio and inertia data, which are aligned by the proposed vibration event-based method. Such information can be used to calibrate the drift of encounter position. The calibrated encounter position is beneficial to most of the floorplan generation steps, such as trace drift elimination, landmark positioning, hallway assembling, and room area estimation. Our experiments in three shopping malls show that CrowdX achieves an average F-measure around 89.4%. In addition, the average estimated room area error within about 20%. The evaluation results demonstrate a significant improvement of accuracy enhanced with opportunistic encounters. © 2018 Association for computing Machinery.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Simulation standardization: Current state and cross-platform system for network simulators 13th

Simulation standardization: Current state and cross-platform...

引用

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

PSVM: a preference-enhanced SVM model using preference data for classification

引用

Science China(information Sciences) 2017年第12期60卷 165-178页

作者： Lerong MA Dandan SONG Lejian LIAO Jingang WANG Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications School of Computer Science and Technology Beijing Institute of Technology College of Mathematics and Computer Science Yan'an University Search Business Department Alibaba Group

Classification is an essential task in data mining, machine learning and pattern recognition *** classification models focus on distinctive samples from different categories. There are fine-grained differences between data instances within a particular category. These differences form the preference information that is essential for human learning, and, in our view, could also be helpful for classification models. In this paper, we propose a preference-enhanced support vector machine(PSVM), that incorporates preference-pair data as a specific type of supplementary information into SVM. Additionally, we propose a two-layer heuristic sampling method to obtain effective preference-pairs, and an extended sequential minimal optimization(SMO)algorithm to fit PSVM. To evaluate our model, we use the task of knowledge base acceleration-cumulative citation recommendation(KBA-CCR) on the TREC-KBA-2012 dataset and seven other datasets from UCI,Stat Lib and ***. The experimental results show that our proposed PSVM exhibits high performance with official evaluation metrics.

关键词： preference SVM classification sampling sequential minimal optimization(SMO)

来源：评论

学校读者我要写书评

暂无评论

Distant supervision for relation extraction with linear attenuation simulation and non-IID relevance embedding

arXiv

引用

arXiv 2018年

作者： Yuan, Changsen Huang, Heyan Feng, Chong Liu, Xiao Wei, Xiaochi Department of Computer Science Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Baidu Inc. China

Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem. However, existing distant supervision methods suffer from selecting important words in the sentence and extracting valid sentences in the bag. Towards this end, we propose a novel approach to address these problems in this paper. Firstly, we propose a linear attenuation simulation to reflect the importance of words in the sentence with respect to the distances between entities and words. Secondly, we propose a non-independent and identically distributed (non-IID) relevance embedding to capture the relevance of sentences in the bag. Our method can not only capture complex information of words about hidden relations, but also express the mutual information of instances in the bag. Extensive experiments on a benchmark dataset have well-validated the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Incorporating target language semantic roles into a string-to-tree translation model

引用

Frontiers of information Technology & Electronic Engineering 2017年第10期18卷 1534-1542页

作者： Chao SU Yu-hang GUO He-yan HUANG Shu-min SHI Chong FENG School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing 100081China Beijing Advanced Innovation Center for Imaging Technology Capital Normal UniversityBeijing 100048China

The string-to-tree model is one of the most successful syntax-based statistical machine translation(SMT) models. It models the grammaticality of the output via target-side syntax. However, it does not use any semantic information and tends to produce translations containing semantic role confusions and error chunk sequences. In this paper, we propose two methods to use semantic roles to improve the performance of the string-to-tree translation model:(1) adding role labels in the syntax tree;(2) constructing a semantic role tree, and then incorporating the syntax information into it. We then perform string-to-tree machine translation using the newly generated trees. Our methods enable the system to train and choose better translation rules using semantic information. Our experiments showed significant improvements over the state-of-the-art string-to-tree translation system on both spoken and news corpora, and the two proposed methods surpass the phrase-based system on large-scale training data.

关键词： Machine translation Semantic role Syntax tree String-to-tree

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：