49,474 Hits in 6.4 sec

Evaluation of a flowchart-based EHR query system: A case study of RetroGuide

Vojtech Huser, Scott P. Narus, Roberto A. Rocha
2010 Journal of Biomedical Informatics  
We developed a prototype of a flowchart-based analytical framework called RetroGuide that enables non-experts to formulate query tasks using a step-based, patient-centered paradigm inspired by workflow  ...  Additional qualitative evaluation results, based on a technology acceptance model, suggested that a fully developed RetroGuide-like technology would be well accepted by users.  ...  RetroGuide uses, as graphical query metaphor, step-based flowchart models (called ''scenarios") to represent queries.  ... 
doi:10.1016/j.jbi.2009.06.001 pmid:19560553 pmcid:PMC2840619 fatcat:mni7aad7yfctvlbcwxpgvgrj6a

Cognitive Functionality based Question Answering System

Ashish Chandiok, D. K.
2018 International Journal of Computer Applications  
An illustration also deliberated and elucidated using a practical implementation and evaluation along with its fundamental cognitive functionality.  ...  A Question Answering (QA) system outdoes the traditional information retrieval search engines in such situations.  ...  The real world models of such systems are BASE-BALL [12] and LUNAR [29] . BASEBALL responded queries on particular leagues of US baseball.  ... 
doi:10.5120/ijca2018916375 fatcat:hvopc3fudbf77l7btg7uexucxu

Generating Intensional Answers in Intelligent Question Answering Systems [chapter]

Farah Benamara
2004 Lecture Notes in Computer Science  
In this paper, we present a logic-based model for an accurate generation of intensional responses within a cooperative questionanswering framework.  ...  Finally, we show that it is possible to generate such NL responses on a template basis.  ...  Evaluating a query is realized in two different ways: -from the deductive knowledge base, in that case, responses are variable instances or, -from the indexed text base, and in that case, responses are  ... 
doi:10.1007/978-3-540-27823-8_2 fatcat:qs5yozsqdraqjm4xj6xjlrvphm

Cognitive Systems and Question Answering [article]

Ulrich Furbach and Claudia Schon and Frieder Stolzenburg
2014 arXiv   pre-print
A possibility to master these challenges is illustrated by a detailed presentation of the LogAnswer system, which is a successful representative of the field of natural language question answering.  ...  This paper briefly characterizes the field of cognitive computing. As an exemplification, the field of natural language question answering is introduced together with its specific challenges.  ...  In such a restricted time, a question cannot be answered directly using the the whole knowl-edge base.  ... 
arXiv:1411.4825v1 fatcat:a3xmmjxxpnc2vaxnkxhb4aahya

Selection-based Question Answering of an MOOC [article]

Atul Sahay, Smita Gholkar, Kavi Arya
2019 arXiv   pre-print
We propose a weighted similarity metric as a measure of matching and find it more reliable than Content-Content or Title-Title similarities alone.  ...  Responding to questions in real-time is a challenge for project staff. Here, we illustrate the advantage of Deep Learning for real-time question answering in the eYRC discussion forum.  ...  Therefore, in our model we try to find semantically similar doubts already in the Knowledge base with a confidence score higher than a predefined baseline(in our case around 70%) to answer a query.  ... 
arXiv:1911.07629v1 fatcat:swpnnhjahngvfpzpheba5mfeb4

Neural factoid geospatial question answering

Haonan Li, Ehsan Hamzei, Ivan Majic, Hua Hua, Jochen Renz, Martin Tomko, Maria Vasardani, Stephan Winter, Timothy Baldwin
2021 Journal of Spatial Information Science  
task, and the graph generation of the query as a semantic dependency parsing task.  ...  We demonstrate that our proposed graph representation approach aids in the translation from natural language to a formal, executable expression in a query language.  ...  Finally, in case of SELECT queries, the intent of questions is derived using a heuristic approach.  ... 
doi:10.5311/josis.2021.23.159 fatcat:mvba3par2zb7zoy7kjv3optryu

Answering conceptual queries with Ferret

Brian de Alwis, Gail C. Murphy
2008 Proceedings of the 13th international conference on Software engineering - ICSE '08  
Programmers attempt to answer these questions, which we call conceptual queries, using a variety of tools.  ...  In addition to presenting this model, we present a tool that implements the model, demonstrate the range of conceptual queries supported by this tool, and present the results of use of the conceptual queries  ...  knowledge-base suitable for answering conceptual queries.  ... 
doi:10.1145/1368088.1368092 dblp:conf/icse/AlwisM08 fatcat:ffx64l5sjbgetbfvg56uyit4ry

Artificial Cognitive Systems That Can Answer Human Creativity Tests: An Approach and Two Case Studies

Ana-Maria Olteteanu, Zoe Falomir, Christian Freksa
2018 IEEE Transactions on Cognitive and Developmental Systems  
Two case studies of artificial cognitive systems evaluated with human creativity tests are reviewed. A general approach is put forward.  ...  The importance of using cognitively viable processes, cognitive knowledge acquisition and organization, and cognitively comparable evaluation when implementing creative problem-solving systems is emphasized  ...  A cup can be used for putting flowers in (based on its similarity of shape with known object V ase).  ... 
doi:10.1109/tcds.2016.2629622 fatcat:jaialckg5ffm5lcis4jwk4jau4

Answer Set Programming [chapter]

Piero Bonatti, Francesco Calimeri, Nicola Leone, Francesco Ricca
2010 Lecture Notes in Computer Science  
Answer Set Programming (ASP), referred to also as Disjunctive Logic Programming under the stable model semantics (DLP), is a powerful formalism for Knowledge Representation and Reasoning.  ...  After a formal definition of ASP, this chapter surveys the main contribution given by the Italian community to the ASP field in the last 25 years.  ...  Various forms of preferences, policies, and cost-based criteria can be used to model the processes that produce/consume resources [54] .  ... 
doi:10.1007/978-3-642-14309-0_8 fatcat:m7vjxp43qfbgjpujf7ozr72x5q

Neural Reasoning, Fast and Slow, for Video Question Answering [article]

Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran
2020 arXiv   pre-print
arriving at a sensible answer.  ...  What does it take to design a machine that learns to answer natural questions about a video?  ...  = ELU(.), (17) Finally, a linear regression is used to output an answer index: s = W y y + b y . (18) The model in this case is trained with hinge loss of pairwise comparisons, max (0, 1 + s n − s p ),  ... 
arXiv:1907.04553v2 fatcat:wzkd3dy3ibewdgr43ojgzyb6yu

Compositional Attention Networks for Interpretability in Natural Language Question Answering [article]

Muru Selvakumar, Suriyadeepan Ramamoorthy, Vaidheeswaran Archana, Malaikannan Sankarasubbu
2018 arXiv   pre-print
The transparent nature of MAC net provides a highly granular view of the reasoning steps taken by the network in answering a query.  ...  MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering.  ...  MACNet A given story forms the basis for the model.The model used takes into account two things, a story and a question which is to be answered by the model.  ... 
arXiv:1810.12698v1 fatcat:zll5pemr4rhatbmjicm2kmuwn4

Training Curricula for Open Domain Answer Re-Ranking [article]

Sean MacAvaney, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Nazli Goharian, Ophir Frieder
2020 arXiv   pre-print
When applied to a BERT-based ranker, our method yields up to a 4% improvement in MRR and a 9% improvement in P@1 (compared to the model trained without a curriculum.  ...  In this work, we apply this idea to the training of neural answer rankers using curriculum learning. We propose several heuristics to estimate the difficulty of a given training sample.  ...  This observation strengthens the case for using curricula when training because it can allow for similar gains as using a much larger model.  ... 
arXiv:2004.14269v1 fatcat:7ivxm62ggbcrxnmxyccgs24nqq

Interactive Answer Set Programming - Preliminary Report [article]

Martin Gebser and Phillip Obermeier and Torsten Schaub
2015 arXiv   pre-print
Traditional Answer Set Programming (ASP) rests upon one-shot solving. A logic program is fed into an ASP system and its stable models are computed.  ...  solver interacts with a user.  ...  Introduction Traditional logic programming [1,2] is based upon query answering.  ... 
arXiv:1511.01261v1 fatcat:hyrf3lpwendk5leacd65j5wd4e

NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets [article]

Victor Dibia
2020 arXiv   pre-print
It introduces and implements contextual query expansion (CQE) using a masked language model (MLM) as well as relevant snippets (RelSnip) - a method for condensing large documents into smaller passages  ...  Existing tools for Question Answering (QA) have challenges that limit their use in practice.  ...  Rather than sifting through lists of retrieved documents, automatic QA (also known as reading comprehension) systems can surface an exact answer to a query, thus reducing the cognitive burden associated  ... 
arXiv:2007.15211v2 fatcat:q5wnqc6awzdw7nsxoyl4ehlb4u

Answering search queries with CrowdSearcher

Alessandro Bozzon, Marco Brambilla, Stefano Ceri
2012 Proceedings of the 21st international conference on World Wide Web - WWW '12  
to the use of search systems, they do it through new queries, loosely related to the previous search or to the social interaction.  ...  The technical contribution of this paper is the discussion of a model and architecture for integrating computerized search with human interaction, by showing how search systems can drive and encapsulate  ...  Crowd Query Answering Based on the query setting, crowds receive an invitation to contribute their opinions.  ... 
doi:10.1145/2187836.2187971 dblp:conf/www/BozzonBC12 fatcat:mmk6ezw5zrffjlgcjozdx37zsy
« Previous Showing results 1 — 15 out of 49,474 results