检索结果-内蒙古大学图书馆

Korean-to-Chinese machine translation using Chinese character as pivot clue 33

学校读者我要写书评

暂无评论

Korean-to-Chinese machine translation using Chinese characte...

33rd Pacific Asia Conference on Language, Information and Computation, PACLIC 2019

作者： Park, Jeonghyeok Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino- Korean words, which can be converted into corresponding Chinese characters, account for more then fifty of the entire Korean vocabulary. Motivated by this, we propose a simple linguistically motivated solution to improve the performance of Korean-to-Chinese neural machine translation model by using their common vocabulary. We adopt Chinese characters as a translation pivot by converting Sino- Korean words in Korean sentence to Chinese characters and then train machine translation model with the converted Korean sentences as source sentences. The experimental results on Korean-to-Chinese translation demonstrate that the models with the proposed method improve translation quality up to 1.5 BLEU points in comparison to the baseline models. Copyright © 2019 Jeonghyeok Park and Hai Zhao.

关键词： Neural machine translation

Code summarization with structure-induced Transformer

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wu, Hongqiu Zhao, Hai Zhang, Min Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Institute of Artificial Intelligence School of Computer Science and Technology Soochow University Suzhou China

Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for programming language in the format of source code, serving in the most convenience of programmer developing. It is well known that programming languages are highly structured. Thus previous works attempt to apply structure-based traversal (SBT) or non-sequential models like Tree-LSTM and graph neural network (GNN) to learn structural program semantics. However, it is surprising that incorporating SBT into advanced encoder like Transformer instead of LSTM has been shown no performance gain, which lets GNN become the only rest means modeling such necessary structural clue in source code. To release such inconvenience, we propose structure-induced Transformer, which encodes sequential code inputs with multi-view structural clues in terms of a newly-proposed structure-induced self-attention mechanism. Extensive experiments show that our proposed structure-induced Transformer helps achieve new state-of-the-art results on benchmarks. Copyright © 2020, The Authors. All rights reserved.

关键词： Trees (mathematics)

The Multi-modality Cell Segmentation Challenge: Towards Universal Solutions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Jun Xie, Ronald Ayyadhury, Shamini Ge, Cheng Gupta, Anubha Gupta, Ritu Gu, Song Zhang, Yao Lee, Gihun Kim, Joonkee Lou, Wei Li, Haofeng Upschulte, Eric Dickscheid, Timo de Almeida, José Guilherme Wang, Yixin Han, Lin Yang, Xin labagnara, Marco Gligorovski, Vojislav Scheder, Maxime Rahi, Sahand Jamal Kempster, Carly Pollitt, Alice Espinosa, Leon Mignot, Tâm Middeke, Jan Moritz Eckardt, Jan-Niklas Li, Wangkai Li, Zhaoyang Cai, Xiaochen Bai, Bizhe Greenwald, Noah F. Van Valen, David Weisbart, Erin Cimini, Beth A. Cheung, Trevor Brück, Oscar Bader, Gary D. Wang, Bo Peter Munk Cardiac Centre University Health Network TorontoON Canada Department of Laboratory Medicine and Pathobiology University of Toronto TorontoON Canada Vector Institute TorontoON Canada Department of Molecular Genetics University of Toronto TorontoON Canada Donnelly Centre University of Toronto TorontoON Canada Princess Margaret Cancer Centre University Health Network TorontoON Canada School of Medicine and Pharmacy Ocean University of China Qingdao China New Delhi India Laboratory Oncology Dr. BRA-IRCH All India Institute of Medical Sciences New Delhi India Department of Image Reconstruction Nanjing Anke Medical Technology Co. Ltd. Nanjing China Shanghai Artificial Intelligence Laboratory Shanghai China Graduate School of AI KAIST Seoul Korea Republic of Shenzhen Research Institute of Big Data Shenzhen China Shenzhen China Helmholtz AI Research Center Jülich Jülich Germany Faculty of Mathematics and Natural Sciences Institute of Computer Science Heinrich Heine University Düsseldorf Düsseldorf Germany Hinxton United Kingdom Champalimaud Foundation - Centre for the Unknown Lisbon Portugal Department of Bioengineering Stanford University Palo AltoCA United States Tandon School of Engineering New York University New YorkNY United States School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China Lausanne Switzerland School of Biological Sciences University of Reading Reading United Kingdom Laboratoire de Chimie Bactérienne CNRS Université Aix Marseille UMR Institut de Microbiologie de la Méditerranée Marseille France Department of Internal Medicine I University Hospital Dresden Technical University Dresden Dresden Germany Else Kroener Fresenius Center for Digital Health Technical University Dresden Dresden Germany Department of Automation University of Science and Technology of China Hefei China Institute of Advanced Technology University of Science and Technology of China Hefei Chi

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimental settings. Here, we present a multi-modality cell segmentation benchmark, comprising over 1500 labeled images derived from more than 50 diverse biological experiments. The top participants developed a Transformer-based deep-learning algorithm that not only exceeds existing methods but can also be applied to diverse microscopy images across imaging platforms and tissue types without manual parameter adjustments. This benchmark and the improved algorithm offer promising avenues for more accurate and versatile cell analysis in microscopy imaging. © 2023, CC BY-NC-ND.

关键词： Deep learning

Not at Home on the Range: Peer Production and the Urban/Rural Divide

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Johnson, Isaac L. Lin, Yilun Jia-Jun Li, Toby Hall, Andrew Halfaker, Aaron Schöning, Johannes Hecht, Brent GroupLens Research Department of Computer Science University of Minnesota Human-Computer Interaction Institute Carnegie Mellon University Wikimedia Foundation Expertise Center for Digital Media Hasselt University - tUL - iMinds

Wikipedia articles about places, OpenStreetMap features, and other forms of peer-produced content have become critical sources of geographic knowledge for humans and intelligent technologies. In this paper, we explore the effectiveness of the peer production model across the rural/urban divide, a divide that has been shown to be an important factor in many online social systems. We find that in both Wikipedia and OpenStreetMap, peer-produced content about rural areas is of systematically lower quality, is less likely to have been produced by contributors who focus on the local area, and is more likely to have been generated by automated software agents (i.e. "bots"). We then codify the systemic challenges inherent to characterizing rural phenomena through peer production and discuss potential solutions. Copyright © 2019, The Authors. All rights reserved.

关键词： Rural areas

Learning better universal representations from pre-trained contextualized language models

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Yian Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

Pre-trained contextualized language models such as BERT (Devlin et al., 2019) have shown great effectiveness in a wide range of downstream natural language processing (NLP) tasks. However, the effective representations offered by the models target at each token inside a sequence rather than each sequence and the fine-tuning step involves the input of both sequences at one time, leading to unsatisfying representation of each individual sequence. Besides, as sentence-level representations taken as the full training context in these models, there comes inferior performance on lower-level linguistic units (phrases and words). In this work, we present a novel framework on BERT that is capable of generating universal, fixed-size representations for input sequences of any lengths, i.e., words, phrases, and sentences, using a large scale of natural language inference and paraphrase data with multiple training objectives. Our proposed framework adopts the Siamese network, learning sentence-level representations from natural language inference dataset and phrase and word-level representations from paraphrasing dataset, respectively. We evaluate our model across different granularity of text similarity tasks, including STS tasks, SemEval2013 Task 5(a) and some commonly used word similarity tasks, where our model substantially outperforms other representation models on sentence-level datasets and achieves significant improvements in word-level and phrase-level representation. Copyright © 2020, The Authors. All rights reserved.

关键词： Natural language processing systems

Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Study

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Luyang Chen, Hao Xiao, Yongjie Zhou, Yanning Wang, Xi Vardhanabhuti, Varut Wu, Mingxiang Han, Chu Liu, Zaiyi Fang, Xin Hao Benjamin Tsougenis, Efstratios Lin, Huangjing Heng, Pheng-Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong AI Research Lab Imsight Technology Co. Ltd. Shenzhen China Department of Diagnostic Radiology Li Ka Shing Faculty of Medicine The University of Hong Kong Hong Kong Department of Radiology Shenzhen People's Hospital Shenzhen Luohu China Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China Department of Radiology Queen Marry Hospital Hong Kong Artificial Intelligence Lab Head Office Information Technology and Health Informatics Division Hospital Authority Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Hong Kong

Purpose To evaluate the ability of fine-grained annotations to overcome shortcut learning in deep learning (DL)-based diagnosis using chest radiographs. Materials and Methods Two DL models were developed using radiograph-level annotations (yes or no disease) and fine-grained lesion-level annotations (lesion bounding boxes), respectively named CheXNet and CheXDet. A total of 34,501 chest radiographs from January 2005-September 2019 were retrospectively collected and annotated with cardiomegaly, pleural effusion, mass, nodule, pneumonia, pneumothorax, tuberculosis, fracture, and aortic calcification. The models' internal classification performance and lesion localization performance were compared on an testing set (n=2,922), external classification performance was compared on NIH-Google (n=4,376) and PadChest (n=24,536) datasets, and external lesion localization performance was compared on NIH-ChestX-ray14 dataset (n=880). The models were also compared to radiologists on a subset of the internal testing set (n=496). Performance was evaluated using receiver operating characteristic curve (ROC) analysis. Results Given sufficient training data, both models performed comparably to radiologists. CheXDet achieved significant improvement for external classification, such as in classifying fracture on NIH-Google (CheXDet area under the ROC curve [AUC]: 0.67, CheXNet AUC: 0.51;p © 2021, CC BY.

关键词： Classification (of information)

An ecologically valid examination of event-based and time-based prospective memory using immersive virtual reality: The influence of attention, memory, and executive function processes on real-world prospective memory.

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kourtesis, Panagiotis MacPherson, Sarah E. Human Cognitive Neuroscience Department of Psychology University of Edinburgh Edinburgh United Kingdom Department of Psychology University of Edinburgh 7 George Square EdinburghEH8 9JZ United Kingdom Lab of Experimental Psychology Suor Orsola Benincasa University of Naples Naples Italy Interdepartmental Centre for Planning and Research "Scienza Nuova" Suor Orsola Benincasa University of Naples Naples Italy National Research Institute of Computer Science and Automation INRIA Rennes France Univ Rennes Rennes France Research Institute of Computer Science and Random Systems IRISA Rennes France French National Centre for Scientific Research CNRS Rennes France

Studies on prospective memory (PM) predominantly assess either event- or time-based PM by implementing non-ecological laboratory-based tasks. The results deriving from these paradigms have provided findings that are discrepant with ecologically valid research paradigms that converge on the complexity and cognitive demands of everyday tasks. The Virtual Reality Everyday Assessment lab (VR-EAL), an immersive virtual reality (VR) neuropsychological battery with enhanced ecological validity, was implemented to assess everyday event- and time-based PM, as well as the influence of other cognitive functions on everyday PM functioning. The results demonstrated the importance of delayed recognition, planning, and visuospatial attention on everyday PM. Delayed recognition and planning ability were found to be central in event- and time-based PM respectively. In order of importance, delayed recognition, visuospatial attention speed, and planning ability were found to be involved in event-based PM functioning. Comparably, planning, visuospatial attention accuracy, delayed recognition, and multitasking/task-shifting ability were found to be involved in time-based PM functioning. These findings further suggest the importance of ecological validity in the study of PM, which may be achieved using immersive VR paradigms. © 2021, CC BY.

关键词： Ecology

Reference Knowledgeable Network for Machine Reading Comprehension

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhao, Yilin Zhang, Zhuosheng Zhao, Hai The Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of specific tasks or complex networks, without explicitly referring to relevant and credible external knowledge sources, which are supposed to greatly make up for the deficiency of the given passage. Thus we propose a novel reference-based knowledge enhancement model called Reference Knowledgeable Network (RekNet), which simulates human reading strategies to refine critical information from the passage and quote explicit knowledge in necessity. In detail, RekNet refines fine-grained critical information and defines it as Reference Span, then quotes explicit knowledge quadruples by the co-occurrence information of Reference Span and candidates. The proposed RekNet is evaluated on three multi-choice MRC benchmarks: RACE, DREAM and Cosmos QA, obtaining consistent and remarkable performance improvement with observable statistical significance level over strong baselines. Our code is available at https://***/Yilin1111/RekNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Complex networks

Adaptive convolution for semantic role labeling

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Munir, Kashif Zhao, Hai Li, Zuchao Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Semantic role labeling (SRL) aims at elaborating the meaning of a sentence by forming a predicate-argument structure. Recent researches depicted that the effective use of syntax can improve SRL performance. However, syntax is a complicated linguistic clue and is hard to be effectively applied in a downstream task like SRL. This work effectively encodes syntax using adaptive convolution which endows strong flexibility to existing convolutional networks. The existing CNNs may help in encoding a complicated structure like syntax for SRL, but it still has shortcomings. Contrary to traditional convolutional networks that use same filters for different inputs, adaptive convolution uses adaptively generated filters conditioned on syntactically-informed inputs. We achieve this with the integration of a filter generation network which generates the input specific filters. This helps the model to focus on important syntactic features present inside the input, thus enlarging the gap between syntax-aware and syntax-agnostic SRL systems. We further study a hashing technique to compress the size of the filter generation network for SRL in terms of trainable parameters. Experiments on CoNLL-2009 dataset confirm that the proposed model substantially outperforms most previous SRL systems for both English and Chinese languages. © 2020, CC0.

关键词： Convolution