Filters








163,834 Hits in 8.0 sec

Computational performance of Java and C++ in processing fMRI datasets

Rodrigo Vivanco, Nicolino Pizzi
2002 Companion of the 17th annual ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications - OOPSLA '02  
Object-oriented programming languages, such as Java and C++ facilitate software reuse and maintainability, and provide the foundations for the development of complex data analysis applications.  ...  This paper explores the advantages and disadvantages of using these two programming environments for scientific computation.  ...  Over time, the intensity level of a given voxel will change if it is involved in the neural processing of a task. Analysis is performed along the time dimension of the data.  ... 
doi:10.1145/985072.985123 dblp:conf/oopsla/VivancoP02 fatcat:3n43fdraancorjs3bvf3vmirri

Robustness Testing of Language Understanding in Task-Oriented Dialog

Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
The augmented dataset through LAUG can be used to facilitate future research on the robustness testing of language understanding in task-oriented dialog.  ...  Most language understanding models in taskoriented dialog systems are trained on a small amount of annotated training data, and evaluated in a small set from the same distribution.  ...  This work was also supported by the Guoqiang Institute of Tsinghua University, with Grant No. 2019GQG1 and 2020GQG0005.  ... 
doi:10.18653/v1/2021.acl-long.192 fatcat:eis2gfsmendftkn3fz4otzwtri

NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation

Sungdong Kim, Minsuk Chang, Sang-Woo Lee
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
In the evaluation, the synthetic dialogue corpus generated from NeuralWOZ achieves a new state-of-theart with improvements of 4.4% point joint goal accuracy on average across domains, and improvements  ...  Collector generates dialogues from (1) user's goal instructions, which are the user context and task constraints in natural language, and (2) system's API call results, which is a list of possible query  ...  Acknowledgments We thank Sohee Yang, Gyuwan Kim, Jung-Woo Ha, and other members of NAVER AI for their valuable comments.  ... 
doi:10.18653/v1/2021.acl-long.287 fatcat:2km727f635c5lojsmwm23ryjgm

PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation

Jing Gu, Qingyang Wu, Chongruo Wu, Weiyan Shi, Zhou Yu
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)   unpublished
However, the performance of pretrained models on task-oriented dialog tasks is still under-explored.  ...  With much less training data, PRAL outperforms or is on par with state-of-the-art models.  ...  Sequicity is the state-of-the-art method in task-oriented dialog tasks that requires annotations.  ... 
doi:10.18653/v1/2021.acl-short.40 fatcat:w5cxjr2ovbacjlmptxpxdxj2zi

Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer

Fabian Galetzka, Jewgeni Rose, David Schlangen, Jens Lehmann
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
The results of our human evaluation show that this encoding reduces space requirements without negative effects on the precision of reproduction of knowledge and perceived consistency.  ...  To improve the coherence and knowledge retrieval capabilities of non-task-oriented dialogue systems, recent Transformer-based models aim to integrate fixed background context.  ...  Acknowledgements We thank our colleagues from the Digital Assistant for Mobility team at the Volkswagen Group Innovation Europe for their support in preparing the human evaluation.  ... 
doi:10.18653/v1/2021.acl-long.546 fatcat:lyqg4jiujjdelh3c34dj3pmwge

RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems

Baolin Peng, Chunyuan Li, Zhu Zhang, Chenguang Zhu, Jinchao Li, Jianfeng Gao
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (  ...  We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per  ...  In a bid to support human-computer interactions, task-oriented dialog systems have been built to allow users to converse with a computer system using natural language, such as Siri, Google Assistant, Amazon  ... 
doi:10.18653/v1/2021.acl-long.341 fatcat:mnddwj75ovgr3fv5xwi4b5noce

Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking

Binzong Geng, Fajie Yuan, Qiancheng Xu, Ying Shen, Ruifeng Xu, Min Yang
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)   unpublished
to alleviate the negative impact of fixed weights of old tasks on new tasks.  ...  This paper proposes an effective continual learning for the task-oriented dialogue system with iterative network pruning, expanding and masking (TPEM), which preserves performance on previously encountered  ...  Acknowledgments This work was partially supported by National Natural Science Foundation of China  ... 
doi:10.18653/v1/2021.acl-short.66 fatcat:zxpjxylxy5fl5mxedimt2yjg4m

Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

Yanan Wu, Zhiyuan Zeng, Keqing He, Hong Xu, Yuanmeng Yan, Huixing Jiang, Weiran Xu
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
NSD aims to discover unknown or out-of-domain slot types to strengthen the capability of a dialogue system based on in-domain training data.  ...  In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task, Novel Slot Detection (NSD), in the task-oriented dialogue system.  ...  Qualitative Analysis Effect of Different Data Processing Strategies In this section, we will dive into the analysis of the effects of different data processing strategies.  ... 
doi:10.18653/v1/2021.acl-long.270 fatcat:usokghe3d5cwjnu4uruqd3iohm

Page 595 of Computational Linguistics Vol. 23, Issue 4 [page]

1997 Computational Linguistics  
In Proceedings of the 1995 International Conference on Computer Processing of Oriental Languages (ICCPOL-95), pages 306-313, Hawaii. Ma, Yan. 1996.  ...  In Proceedings of the 1992 International Conference on Computer Processing of Chinese and Oriental Languages, pages 17-23. Li, Wen-Jie, H-H. Pan, M. Zhou, K-F. Wong, and V. Lum. 1995.  ... 

IALP 2020 TOC

2020 2020 International Conference on Asian Language Processing (IALP)  
VIII About the Conference The International Conference on Asian Language Processing (IALP) is the flagship conference of the Chinese and Oriental Languages Information Processing Society (COLIPS).  ...  Starting as the 1st International Conference in Chinese Computing 34 years ago in 1986, the annual flagship conference of the Chinese and Oriental Languages Information Processing Society (COLIPS), has  ... 
doi:10.1109/ialp51396.2020.9310474 fatcat:omzdo6c2sbcsjk3umujct3f7ky

Page 374 of Computational Linguistics Vol. 17, Issue 4 [page]

1991 Computational Linguistics  
International Conference of Computer Processing and Oriental Languages. Chen, J. J. (1985). “An experimental parsing system for Chinese sentences,” M.S. thesis, National Taiwan University, Taipei.  ...  “Chart parsing according to the slot and filler principle.” In Proceedings, International Conference on Computational Linguistics, 242-244. Ho, W. H. (1984). “Automatic recognition of Chinese words.”  ... 

Elicitation of Non-functional Requirement Preference for Actors of Usecase from Domain Model [chapter]

G. S. Anandha Mala, G. V. Uma
2006 Lecture Notes in Computer Science  
International / National Conference Proceedings: 1.College of ISO-Picture Languages, Procedings of the International Conference on Mathematics and Computer science 2008, pp 222-229 2.  ...  Area of Specializations : Natural Language Processing, Object Oriented Analysis and Design 7.  ... 
doi:10.1007/11961239_23 fatcat:dg6msn5xebaofl37ixdcxmhpam

Tutorial session services oriented architecture and semantic web processes

F. Curbera, A. Sheth, K. Verma
2004 Proceedings. IEEE International Conference on Web Services, 2004.  
It presents the more recent evolution of the Web service platform towards rich Web service and process model annotation,  ...  This tutorial presents what can be achieved by symbiotic synthesis of two of the hottest R&D and technology application areas: Web services and the Semantic Web.  ...  Kunal Verma is a research assistant and PhD student in the Computer Science department at the University of Georgia. His research interests span Web processes, databases and the Semantic Web.  ... 
doi:10.1109/icws.2004.1314712 fatcat:yfejqdcwl5fwnlvnzvvqzqv5ba

Hybrid web service composition

Anis Charfi, Mira Mezini
2004 Proceedings of the 2nd international conference on Service oriented computing - ICSOC '04  
These languages define the composition on the basis of a process that specifies the control and data flow among the services to be composed.  ...  Over the last few years several process-based web service composition languages have emerged, such as BPEL4WS and BPML.  ...  The process specifies the order of invocations (control flow) and rules for data transfer between them (data flow).  ... 
doi:10.1145/1035167.1035173 dblp:conf/icsoc/CharfiM04 fatcat:klksogkt3zbbzl2eyj4yyx6kem

Page 574 of Computational Linguistics Vol. 31, Issue 4 [page]

2005 Computational Linguistics  
In Proceedings of the 2002 International Conference on Computational Linguistics. Sproat, Richard, Alan W. Black, Stanley Chen, Shankar Kumar, Mari Ostendorf, and Christoper Richards. 2001.  ...  I Proceedings of the 2002 International Conference on Compu pages 967-973. Sun, Jian, Ming Zhou, and Jianfeng Gao. 2003. Chinese named entity identification using class-based language model.  ... 
« Previous Showing results 1 — 15 out of 163,834 results