检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Liang, Shining Shou, Linjun Pei, Jian Gong, Ming Zuo, Wanli Zuo, Xianglin Jiang, Daxin College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering MOE China STCA Microsoft Department of Electrical & Computer Engineering Duke University United States

Despite the great success of spoken language understanding (SLU) in high-resource languages, it remains challenging in low-resource languages mainly due to the lack of labeled training data. The recent multilingual code-switching approach achieves better alignments of model representations across languages by constructing a mixed-language context in zero-shot cross-lingual SLU. However, current code-switching methods are limited to implicit alignment and disregard the inherent semantic structure in SLU, i.e., the hierarchical inclusion of utterances, slots, and words. In this paper, we propose to model the utterance-slot-word structure by a multi-level contrastive learning framework at the utterance, slot, and word levels to facilitate explicit alignment. Novel code-switching schemes are introduced to generate hard negative examples for our contrastive learning framework. Furthermore, we develop a label-aware joint model leveraging label semantics to enhance the implicit alignment and feed to contrastive learning. Our experimental results show that our proposed methods significantly improve the performance compared with the strong baselines on two zero-shot cross-lingual SLU benchmark datasets. © 2022, CC BY-NC-ND.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Automatic Life Event Tree Generation for Older Adults 1

引用

24th International Conference on Human-Computer Interaction, HCII 2022

作者： Gui, Fang Wu, Xi Hu, Min Yang, Jiaoyun School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

Studies have shown that learning personal stories could help provide individualized eldercare services. However, personal stories are often disordered because of the scattered collection, including informal interviews or daily interactions, which brings difficulties in acquiring valuable information quickly. One solution to this problem is to extract events from personal stories and automatically organize them in chronological order. Events extracted by current methods from social media or news corpus are mainly organized in a linear structure. These works usually focus on the event time and ignore the consistency of event contents when organizing events. This paper aims to organize events into a tree structure based on an event network, with stem nodes representing key event topics and branch nodes representing detailed events. Social workers or caregivers can clarify the life experience of the older adults quickly through the event tree and have a preliminary understanding of them. The experiments show that the event tree generated by our method has a better performance in consistency than current event organization methods. A survey study shows that our method achieves the highest logical coherence for the event tree branches compared with other algorithms. © 2022, Springer Nature Switzerland AG.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

More Grounded Image Captioning by Distilling Image-Text Matching Model

More Grounded Image Captioning by Distilling Image-Text Matc...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuanen Zhou Meng Wang Daqing Liu Zhenzhen Hu Hanwang Zhang Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) School of Computer Science and Information Engineering Hefei University of Technology University of Science and Technology of China Nanyang Technological University

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from *** improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong *** this end, we propose a Part-of-Speech (POS) enhanced image-text matching model (SCAN[24]): POS-SCAN, as the effective knowledge distillation for more grounded image captioning. The benefits are two-fold: 1) given a sentence and an image, POS-SCAN can ground the objects more accurately than SCAN; 2) POS-SCAN serves as a word-region alignment regularization for the captioner's visual attention module. By showing benchmark experimental results, we demonstrate that conventional image captioners equipped with POS-SCAN can significantly improve the grounding accuracy without strong supervision. Last but not the least, we explore the indispensable Self-Critical Sequence Training (SCST[46]) in the context of grounded image captioning and show that the image-text matching score can serve as a reward for more grounded captioning 1 .

关键词： Visualization Grounding Task analysis Training Measurement Computational modeling Image edge detection

来源：评论

学校读者我要写书评

暂无评论

TransD-based Multi-hop Meta Learning for Few-shot knowledge Graph Completion

TransD-based Multi-hop Meta Learning for Few-shot Knowledge ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jindi Li Kui Yu Yuling Li Yuhong Zhang Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Few-shot knowledge graph completion (FKGC), which aims to infer missing facts about a relation from only a few reference triples, has recently attracted great attention. The core of solving the FKGC task is to learn a vector representation for each few-shot relation using the corresponding entity represen-tations. To this end, existing models generally enhance entity representations with their direct neighbors. However, a large number of entities have few direct neighbors. Hence, encoding only direct neighborhood is insufficient to obtain satisfactory en-tity representations. In addition, current models typically utilize static embeddings to represent entities, ignoring their diverse semantics, i.e., an entity may show distinct semantics within different few-shot relations. To address these issues, we propose a new FKGC framework, namely TransD-based Multi-hop Meta Learning (TDML). TDML consists of three main components: a multi-hop neighbor encoder to enhance entity representations by aggregating heterogeneous multi-hop neighbors, a transformer encoder to generate the relation meta representations, and a TransD-based relation representation updater that allows each entity to exhibit relation-specific semantics and tune the relation meta representations. Extensive experiments on two public datasets demonstrate that our model outperforms state-of-the-art FKGC methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

arXiv

引用

arXiv 2022年

作者： Liu, Kang Xue, Feng Guo, Dan Wu, Le Li, Shujie Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Key Laboratory of Knowledge Engineering with Big Data Intelligent Interconnected Systems Laboratory of Anhui Province 485 Danxia Road Anhui Province Hefei230601 China Hefei University of Technology School of Software Key Laboratory of Knowledge Engineering with Big Data Intelligent Interconnected Systems Laboratory of Anhui Province 485 Danxia Road Anhui Province Hefei230601 China

In most E-commerce platforms, whether the displayed items trigger the user's interest largely depends on their most eye-catching multimodal content. Consequently, increasing efforts focus on modeling multimodal user preference, and the pressing paradigm is to incorporate complete multimodal deep features of the items into the recommendation module. However, the existing studies ignore the mismatch problem between multimodal feature extraction (MFE) and user interest modeling (UIM). That is, MFE and UIM have different emphases. Specifically, MFE is migrated from and adapted to upstream tasks such as image classification. In addition, it is mainly a content-oriented and non-personalized process, while UIM, with its greater focus on understanding user interaction, is essentially a user-oriented and personalized process. Therefore, the direct incorporation of MFE into UIM for purely user-oriented tasks, tends to introduce a large number of preference-independent multimodal noise and contaminate the embedding representations in UIM. This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences. Towards this end, we develop a novel model, multimodal entity graph collaborative filtering, short for MEGCF. The UIM of the proposed model captures the semantic correlation between interactions and the features obtained from MFE, thus making a better match between MFE and UIM. More precisely, semantic-rich entities are first extracted from the multimodal data, since they are more relevant to user preferences than other multimodal information. These entities are then integrated into the user-item interaction graph. Afterwards, a symmetric linear Graph Convolution Network (GCN) module is constructed to perform message propagation over the graph, in order to capture both high-order semantic correlation and collaborative filtering signals. Finally, the sentiment information fr

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing parameters of algorithm trading strategies using MapReduce

Optimizing parameters of algorithm trading strategies using ...

引用

International Conference on Fuzzy Systems and knowledge Discovery (FSKD)

作者： Xiongpai Qin Huiju Wang Furong Li Jidong Chen Xuan Zhou Xiaoyong Du Shan Wang Key Laboratory of Data Engineering and Knowledge Engineering (RUC) Ministry of Education Beijing China School of Information Renmin University of China Beijing China EMC-Greenplum Research China China

In algorithm trading, computer algorithms are used to make the decision on the time, quantity, and direction of operations (buy, sell, or hold) automatically. To create a useful algorithm, the parameters of the algorithm should be optimized based on historical data. However, Parameter optimization is a time consuming task, due to the large search space. We propose to search the parameter combination space using the MapReduce framework, with the expectation that runtime of optimization be cut down by leveraging the parallel processing capability of MapReduce. This paper presents the details of our method and some experiment results to demonstrate its efficiency. We also show that a rule based strategy after being optimized performs better in terms of stability than the one whose parameters are arbitrarily preset, while making a comparable profit.

关键词： Optimization Measurement Computers Algorithm design and analysis Runtime Servers data processing

来源：评论

学校读者我要写书评

暂无评论

PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs

arXiv

引用

arXiv 2024年

作者： Ji, Shengwei Tian, Yujie Liu, Fei Li, Xinlu Wu, Le The School of Artificial Intelligence and Big Data Hefei University Hefei China The School of Computer Science and Information Engineering Hefei University of Technology Hefei China The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education China

Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbn-products graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgraphs, i.e., GCNs can only be trained based on subgraphs instead of global graph information, which reduces the accuracy of GCNs. In this paper, we propose PromptGCN, a novel prompt-based lightweight GCN model to bridge the gaps among subgraphs. First, the learnable prompt embeddings are designed to obtain global information. Then, the prompts are attached into each subgraph to transfer the global information among subgraphs. Extensive experimental results on seven large-scale graphs demonstrate that PromptGCN exhibits superior performance compared to baselines. Notably, PromptGCN improves the accuracy of subgraph sampling methods by up to 5.48% on the Flickr dataset. Overall, PromptGCN can be easily combined with any subgraph sampling method to obtain a lightweight GCN model with higher accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Subject Event Extraction from Chinese Court Verdict Case via Frame-filling

Subject Event Extraction from Chinese Court Verdict Case via...

引用

IEEE International Conference on Big knowledge (ICBK)

作者： Gongqing Wu Shengjie Hu Yinghuan Wang Zan Zhang Xianyu Bao Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China Shenzhen Academy of Inspection and Quarantine Shenzhen China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

At present, the query and acquisition of the fragmented knowledge in Chinese court verdicts mainly adopt the class case retrieval method based on the search engine and the rough extraction method for a part of the data in court verdicts. These traditional methods cannot structurally extract fragmented knowledge in Chinese court verdicts and meet the needs of people for the follow-up analysis of court verdicts. Thus, in this paper, we present a structured subject event extraction method (SEE) for Chinese court verdict cases combining with techniques of event extraction (EE) and attribute-value pair extraction (AVPE). Specifically, we provide a subject event representation frame for organizing fragmented knowledge in Chinese court verdict cases. Then, we extract subject events from the unstructured cases based on the trained sequence labeling models and constructed heuristic rules, and fill them into the subject event representation frame in the form of attribute-value pairs (AVPs). The experimental results show that SEE can efficiently and automatically extract subject events from Chinese court verdict cases and visually display them via frame-filling, which promotes the efficiency of people in searching for legal materials and facilitates further research and analysis.

关键词： Feature extraction data mining Labeling Information retrieval Semantics Machine learning knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

A key-phrase Extraction Method Based on Multi-size Convolution Windows for Scientific Literatures

A Key-phrase Extraction Method Based on Multi-size Convoluti...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yuhong Zhang Yuxin Xie Peipei Li Xuegang Hu Ministry of Education Ministry of Education Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Hefei Hefei University of Technology Hefei China

ISBN: (纸本)9781665441506

The key-phrase extraction is important for the downstream tasks in natural language process, and has attracted a lot of attention. Compared with other documents, scientific literatures contain many long phrases. Most existing methods perform poor on these literatures. To address this problem, a key-phrase extraction method based on multi-size convolution windows (KE-MCW) is proposed for scientific literatures in this paper. More specifically, in order to represent more contextual information, a convolutional neural network(CNN) with multi-size filters is introduced to map the documents into distributed feature vectors, then each vector can represent different size phrases. Next, in order to determine whether each word is a part of a keyphrase, a deep recurrent neural network is used to mark the role of each word. Finally, the attention mechanism is used to further judge the importance of each phrase. Experimental results show that our proposed method performs better than some competitive methods for technology literatures.

关键词： Cloud computing Recurrent neural networks Convolution Conferences Natural languages Information filters Feature extraction

来源：评论

学校读者我要写书评

暂无评论

引用

Journal of Convergence Information Technology 2012年第16期7卷 87-96页

作者： Minjuan, Zhong School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang 330013 China

With the increasing of XML data over the Internet, managing and analyzing huge amount of XML documents has played an important role for information management. Clustering as an intelligent technique has been utilized as an excellent way of grouping the documents by their content or structure. However, the key problem is how to measure similarity between XML documents. In this paper, we propose an extended vector space model and on this basis put forward an effective semantic similarity measurement method combining content and structure semantics, in which a variety of XML document features impacting similarity measurement, such as term element frequency, term inverse element frequency, semantic weight of tag and level information of the term, are analyzed. In addition, information gain, for clustering quality evaluation are introduced motivated by the fact that collection has no classification information in advance. Experiment results show that proposed similarity method (EVSM_SS) outperforms the content and structure integration measurement based on structure path (VSM_SP) as well as traditional document clustering measurement (CO) in information gain and produce better clustering quality.

关键词： XML

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：