Proceedings of the AAAI Conference on Artificial Intelligence
Technical support domain involves solving problems from user queries through various channels: vo... more Technical support domain involves solving problems from user queries through various channels: voice, web and chat, and is both time-consuming and labour intensive. The textual queries in web or chat mode are unstructured and often incomplete. This affects information retrieval and increases the difficulty level for agents to solve it. Such cases require multiple rounds of interaction between user and agent/chatbot in order to better understand the user query. This paper presents a deployed system called Question Quality Improvement (QQI), that aims to improve the quality of user utterance by understanding and extracting important parts of an utterance and gamifying the user interface, prompting them to enter the remaining relevant information. QQI is guided by an ontology designed for the technical support domain and uses co-reference resolution and deep parsing to understand the sentences. Using the syntactics and semantics in the deep parse tree structure various attributes in th...
We consider the problem of computing traffic engineered paths for bandwidth requests, when these ... more We consider the problem of computing traffic engineered paths for bandwidth requests, when these requests arrive in the network independent of one another. Reservation of bandwidth along pre-selected paths have become important in networks providing service ...
I. INTRODUCTION Recently a lot of research attention has been directed to Quality of Service (QoS... more I. INTRODUCTION Recently a lot of research attention has been directed to Quality of Service (QoS) routing [3]. Offering differentiation of services and service guarantees in networks is promising to be a major revenue collector for service providers. This has increased the importance ...
To cope with exponential growth of traffic on the Internet, IP networks require routers capable o... more To cope with exponential growth of traffic on the Internet, IP networks require routers capable of much higher performance capabilities. This has led to interest in combining speed of layer-2 switching with scalability of layer-3 routing, leading to the generation of ...
Proceedings of the 8th ACM/IFIP/USENIX international conference on Middleware - Middleware '07, 2007
The execution of workflow applications is a reality today in enterprise and scientific grid domai... more The execution of workflow applications is a reality today in enterprise and scientific grid domains. The core middleware technologies for grids (e.g. meta-schedulers) contain sophisticated resource matching logic, but lack control flow orchestration capability. Workflow orchestrators, on the other hand, suitably control business logic but are unaware of execution requirements of tasks. Marriage of the scheduling technology with workflow management
1 IBM India Research Lab, New Delhi, India, {gdasgupt, bviswana}@in.ibm.com 2 South Dakota State ... more 1 IBM India Research Lab, New Delhi, India, {gdasgupt, bviswana}@in.ibm.com 2 South Dakota State University, Brookings, SD, USA, onyeka.ezenwoye@sdstate.edu 3 IBM Watson Research Center, Hawthorne, NY, USA, llfong@us.ibm.com 4 Florida International University (FIU), ...
Proceedings of the AAAI Conference on Artificial Intelligence
Technical support domain involves solving problems from user queries through various channels: vo... more Technical support domain involves solving problems from user queries through various channels: voice, web and chat, and is both time-consuming and labour intensive. The textual queries in web or chat mode are unstructured and often incomplete. This affects information retrieval and increases the difficulty level for agents to solve it. Such cases require multiple rounds of interaction between user and agent/chatbot in order to better understand the user query. This paper presents a deployed system called Question Quality Improvement (QQI), that aims to improve the quality of user utterance by understanding and extracting important parts of an utterance and gamifying the user interface, prompting them to enter the remaining relevant information. QQI is guided by an ontology designed for the technical support domain and uses co-reference resolution and deep parsing to understand the sentences. Using the syntactics and semantics in the deep parse tree structure various attributes in th...
We consider the problem of computing traffic engineered paths for bandwidth requests, when these ... more We consider the problem of computing traffic engineered paths for bandwidth requests, when these requests arrive in the network independent of one another. Reservation of bandwidth along pre-selected paths have become important in networks providing service ...
I. INTRODUCTION Recently a lot of research attention has been directed to Quality of Service (QoS... more I. INTRODUCTION Recently a lot of research attention has been directed to Quality of Service (QoS) routing [3]. Offering differentiation of services and service guarantees in networks is promising to be a major revenue collector for service providers. This has increased the importance ...
To cope with exponential growth of traffic on the Internet, IP networks require routers capable o... more To cope with exponential growth of traffic on the Internet, IP networks require routers capable of much higher performance capabilities. This has led to interest in combining speed of layer-2 switching with scalability of layer-3 routing, leading to the generation of ...
Proceedings of the 8th ACM/IFIP/USENIX international conference on Middleware - Middleware '07, 2007
The execution of workflow applications is a reality today in enterprise and scientific grid domai... more The execution of workflow applications is a reality today in enterprise and scientific grid domains. The core middleware technologies for grids (e.g. meta-schedulers) contain sophisticated resource matching logic, but lack control flow orchestration capability. Workflow orchestrators, on the other hand, suitably control business logic but are unaware of execution requirements of tasks. Marriage of the scheduling technology with workflow management
1 IBM India Research Lab, New Delhi, India, {gdasgupt, bviswana}@in.ibm.com 2 South Dakota State ... more 1 IBM India Research Lab, New Delhi, India, {gdasgupt, bviswana}@in.ibm.com 2 South Dakota State University, Brookings, SD, USA, onyeka.ezenwoye@sdstate.edu 3 IBM Watson Research Center, Hawthorne, NY, USA, llfong@us.ibm.com 4 Florida International University (FIU), ...
Uploads
Papers by Gargi Dasgupta