Filters








42,407 Hits in 5.2 sec

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks

Zehao Lin, Xinjing Huang, Feng Ji, Haiqing Chen, Yin Zhang
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
However, existing memory networks do not perform well when leveraging heterogeneous information from different sources.  ...  In this paper, we propose a novel and versatile external memory networks called Heterogeneous Memory Networks (HMNs), to simultaneously utilize user utterances, dialogue history and background knowledge  ...  Proposed Framework To generate responses using dialogue history and grounding knowledge, we introduce a novel encoder-decoder neural conversation model augmented with Heterogeneous Memory Networks (HMNs  ... 
doi:10.18653/v1/d19-1463 dblp:conf/emnlp/LinHJCZ19 fatcat:djelamkro5cpvi3qo5zpuftfne

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks [article]

Zehao Lin, Xinjing Huang, Feng Ji, Haiqing Chen, Ying Zhang
2019 arXiv   pre-print
However, existing memory networks do not perform well when leveraging heterogeneous information from different sources.  ...  In this paper, we propose a novel and versatile external memory networks called Heterogeneous Memory Networks (HMNs), to simultaneously utilize user utterances, dialogue history and background knowledge  ...  Proposed Framework To generate responses using dialogue history and grounding knowledge, we introduce a novel encoder-decoder neural conversation model augmented with Heterogeneous Memory Networks (HMNs  ... 
arXiv:1909.11287v1 fatcat:lilx5hyyljej7janwebybltzau

Mach and Matchmaker: kernel and language support for object-oriented distributed systems

Michael B. Jones, Richard F. Rashid
1986 Conference proceedings on Object-oriented programming systems, languages and applications - OOPLSA '86  
Their usage together providing a heterogeneous, distributed, object-oriented programming environment is described. Performance and usage statistics are presented.  ...  Mach, a multiprocessor operating system kernel providing capability-based interprocess communication, and Matchmaker, a language for specifying and automating the generation of multi-lingual interprocess  ...  The network message server was originally written by Rick Rashid, and is being rewritten for Mach by Dan Julin, Robert Sansom and Ed Zayas.  ... 
doi:10.1145/28697.28705 dblp:conf/oopsla/JonesR86 fatcat:ldyykihal5hrrf627w4qqdlzym

Data fusion methods in multimodal human computer dialog

Ming-Hao YANG, Jian-Hua TAO
2019 Virtual Reality & Intelligent Hardware  
Intelligence methods of multi-modal information fusion in human-computer interaction SCIENTIA SINICA Informationis 48, 433 (2018); Rapid and High-quality 3D Fusion of Heterogeneous CT and MRI Data for  ...  We first introduce the cognitive assumption of single channel processing, and then discuss its implementation methods in human computer dialog; for the task of multi-modal information fusion, serval computing  ...  Generally, we need to consider two types of multi-modal human computer dialog tasks: Task-Oriented and Non-Task-Oriented dialog.  ... 
doi:10.3724/sp.j.2096-5796.2018.0010 dblp:journals/vrih/YangT19 fatcat:jltufn3o6fd4pjzv4pnqd6wmvy

Recent Advances and Challenges in Task-oriented Dialog System [article]

Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu
2020 arXiv   pre-print
In this paper, we survey recent advances and challenges in task-oriented dialog systems.  ...  Besides, we review the recent progresses in dialog evaluation and some widely-used corpora.  ...  [126] proposed to model heterogeneous information using historical information, which is stored in a context-aware memory, and the knowledge base tuples are stored in a context-free memory.  ... 
arXiv:2003.07490v3 fatcat:powcuixxargkbp57kpwmjict3y

An object model for uniform access to heterogeneous databases

P A Schoening, C A Abrams, M G Kahn
1993 Proceedings. Symposium on Computer Applications in Medical Care  
Using object-oriented techniques, the solution identifies the commonality among database management systems and provides a uniform method of communication between applications and databases.  ...  When the data are no longer needed a simple delete allows that memory to be reclaimed for future use.  ...  The task of learning to use each API falls on the programmer who then must concentrate more on the details of data retrieval than on the issues of data utilization.  ... 
pmid:8130524 pmcid:PMC2850628 fatcat:xqotsebz35dyvjh2cwq2l4srhu

Measuring the Impact of Alternative Parallel Process Architectures on Communication Subsystem Performance [chapter]

Douglas C. Schmidt, Tatsuya Suda
1995 IFIP Advances in Information and Communication Technology  
To effectively parallelize a communication subsystem, careful consideration must be given to the process architecture used to structure multiple processing elements.  ...  These experiments measure the impact of the process architecture on connectionless and connection-oriented protocol stacks (based upon UDP and TCP) in a sharedmemory multi-processor operating system.  ...  This conversion processing involves byte-order conversions, as well as dynamic memory allocation and deallocation.  ... 
doi:10.1007/978-0-387-34885-8_8 fatcat:qzhzokjierb5xcdjazryc4airu

HyperFlow: A Heterogeneous Dataflow Architecture [article]

Huy T. Vo, Daniel K. Osmari, João Comba, Peter Lindstrom, Cláudio T. Silva
2012 Eurographics Symposium on Parallel Graphics and Visualization  
First, we designed a general suite of micro-benchmarks that captures main parallel pipeline structures and allows evaluation of HyperFlow under different stress conditions.  ...  We propose a dataflow architecture, called HyperFlow, that offers a supporting infrastructure that creates an abstraction layer over computation resources and naturally exposes heterogeneous computation  ...  Task-Oriented Modules (TOMs) A pipeline in HyperFlow consists of a set of interconnected Task-Oriented Modules (TOMs).  ... 
doi:10.2312/egpgv/egpgv12/001-010 fatcat:k7xndi4fqnhdnnsp2wju2tgdri

Enabling direct connectivity between heterogeneous objects in the internet of things through a network-service-oriented architecture

Eli De Poorter, Ingrid Moerman, Piet Demeester
2011 EURASIP Journal on Wireless Communications and Networking  
Afterward, Section V describes how IDRA can be used to support two typical internet of things use cases: (1) supporting backward compatibility with legacy networks and (2) bridging networks using different  ...  These objects can be very diverse in terms of the used network protocols and communication technologies, which leads to a wild growth of co-located networking technologies.  ...  Network services By delegating common tasks, such as buffer management, packet creation, QoS management and aggregation, IDRA network services require up to a factor 2-10 less memory than traditional network  ... 
doi:10.1186/1687-1499-2011-61 fatcat:6puawjlwpzeyzplsxjutsvdd6y

Back to the future

Michele Zanella, Giuseppe Massari, Andrea Galimberti, William Fornaciari
2018 Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications - INTESA '18  
This would play a key role, especially for emerging use cases, where huge amount of data are generated.  ...  However, the deployment of distributed applications on such an heterogeneous infrastructures requires suitable management layers.  ...  Left: Task-services dependency and conversations (e.g., task T 1 specifies the conversation of services Sa and Sb. Right: the composed final conversation.  ... 
doi:10.1145/3285017.3285028 dblp:conf/esweek/ZanellaMGF18 fatcat:q7ew2illufhp5iakulprghy7i4

Coordinating complex problem-solving among distributed intelligent agents

Richard M. Adler
1992 Telematics and informatics  
However, they do not im- plement generic distributed services in uniform, object-oriented layers that are accessible to devel- opers for customizing.  ...  Object-Oriented Heterogeneous Distributed Computing with Meta- Courier. Technical Report, Cambridge, Mas- sachusetts. Zweben, M. and Gargan, R. (1990).  ... 
doi:10.1016/s0736-5853(05)80036-x fatcat:lvxn5l4dwfgktkmvcgss55hkzm

Review on the Cloud Computing Programming Model

Chao Shen, Weiqin Tong
2014 International Journal of Advanced Science and Technology  
A cloud computing programming model is urgent to design to help user to use cloud resources without concerning the details of implementation.  ...  Cloud computing integrates vast computing and/or storage resources together, which provides services on demand via network.  ...  It is used to processes graph by BSP model. BSPCloud [17] is a hybrid of distributed-memory and shared-memory bulk synchronous parallel (BSP) programming model.  ... 
doi:10.14257/ijast.2014.70.02 fatcat:etcuk75oczgabewmzo62sokii4

Performance Analysis and Modeling of Video Transcoding Using Heterogeneous Cloud Services [article]

Xiangbo Li, Mohsen Amini Salehi, Yamini Joshi, Mahmoud Darwich, Brad Landreneau, Magdy Bayoumi
2018 arXiv   pre-print
VM type for various transcoding tasks.  ...  Cloud providers offer heterogeneous computational services in form of different types of Virtual Machines (VMs) with diverse prices.  ...  [32] studied application-oriented performance analysis using heterogeneous cloud services.  ... 
arXiv:1809.06529v1 fatcat:iv5ugbzxovdelmtqx2jmjgyeda

User Memory Reasoning for Conversational Recommendation [article]

Hu Xu, Seungwhan Moon, Honglei Liu, Bing Liu, Pararth Shah, Bing Liu, Philip S. Yu
2020 arXiv   pre-print
For this study, we create a new Memory Graph (MG) <--> Conversational Recommendation parallel corpus called MGConvRex with 7K+ human-to-human role-playing dialogs, grounded on a large-scale user memory  ...  We study a conversational recommendation model which dynamically manages users' past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph,  ...  The updates are short-term and very close to a task-oriented dialog system.  ... 
arXiv:2006.00184v1 fatcat:dy3hro3smba7ta4obhyohlnyoy

Robust Conversational AI with Grounded Text Generation [article]

Jianfeng Gao, Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Heung-Yeung Shum
2020 arXiv   pre-print
GTG is a hybrid model which uses a large-scale Transformer neural network as its backbone, combined with symbol-manipulation modules for knowledge base inference and prior knowledge encoding, to generate  ...  The primary results reported on task-oriented dialog benchmarks are very promising, demonstrating the big potential of this approach.  ...  Introduction The long-term mission of conversational AI research is to develop at scale conversational assistant systems, also known as task-oriented bots or task bots in short, which are robust enough  ... 
arXiv:2009.03457v1 fatcat:2462mlxn7fg3zgw5mwknoqngaa
« Previous Showing results 1 — 15 out of 42,407 results