20,349 Hits in 10.7 sec

Connecting Question Answering and Conversational Agents

Ulli Waltinger, Alexa Breuing, Ipke Wachsmuth
2012 Künstliche Intelligenz  
We show that the resulting contextualization method contributes to an improvement of existing question answering systems and enhances their application within interactive scenarios.  ...  Thereby we focus on improving the conversational abilities of existing interactive interfaces by enhancing their underlying QA systems in terms of response time and correctness.  ...  Conclusions This work described a question contextualization approach for a German interactive question answering system employed within the architecture of the conversational agent Max.  ... 
doi:10.1007/s13218-012-0208-1 fatcat:7nyicxslqzczvlyv4hdvuoumce

Perceptions on Authenticity in Chat Bots

Mario Neururer, Stephan Schlögl, Luisa Brinkschulte, Aleksander Groth
2018 Multimodal Technologies and Interaction  
Results suggest that showcasing a transparent purpose, learning from experience, anthropomorphizing, human-like conversational behavior, and coherence, are guiding characteristics for agent authenticity  ...  Interviews and an open question survey with experts from different fields have led to a shared understanding of what it would take to make intelligent virtual agents, in particular messaging agents (i.e  ...  two-way learning strategies where it autonomously learns from cultural, behavioral, personal, conversational and contextual interaction data  ... 
doi:10.3390/mti2030060 fatcat:flfbj2cce5bhdcm4azuu2l3bqu

A multi-agent conversational system with heterogeneous data sources access

Eduardo M. Eisman, María Navarro, Juan Luis Castro
2016 Expert systems with applications  
, a FPU scholarship from the Ministry of Education and Science, a Torres Quevedo research contract from the Ministry of Science and Innovation, and the King Abdullah University of Science and Technology  ...  This work has been partially supported by the Spanish Ministry of Science and Technology under research project TIN2007-67984-C02-01, the regional Andalusian Government under research project TIC-P06-01424  ...  Like most conversational agents, she has a memory and is able to answer a quite broad set of general questions (e.g. personal information, or hobbies).  ... 
doi:10.1016/j.eswa.2016.01.033 fatcat:rxtab3emwzcpvebbwyphb7mubi

A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge [article]

Jan Chorowski, Adrian Łańcucki, Szymon Malik, Maciej Pawlikowski, Paweł Rychlikowski, Paweł Zykowski
2018 arXiv   pre-print
To answer questions, our dialogue system relies heavily on factual data, sourced mostly from Wikipedia and DBpedia, data of real user interactions in public forums, as well as data concerning general literature  ...  The primary functionality of our dialogue system is context-aware question answering (QA), while its secondary function is maintaining user engagement.  ...  Acknowledgements The authors want to thank the NIPS 2017 Conversational Intelligence Challenge for organizing the competition, and especially Valentin Malykh for help with resolving technical issues with  ... 
arXiv:1805.08032v1 fatcat:q7fetfwih5cbbcttle44vokqby

The Context-Dependent Additive Recurrent Neural Net

Quan Hung Tran, Tuan Lai, Gholamreza Haffari, Ingrid Zukerman, Trung Bui, Hung Bui
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
The experimental results on public datasets in the dialog problem (Babi dialog Task 6 and Frame), contextual language model (Switchboard and Penn Discourse Tree Bank) and question answering (TrecQA) show  ...  Contextual sequence mapping is one of the fundamental problems in Natural Language Processing.  ...  We experiment with our models on a broad range of problems: dialog systems, contextual language modelling and question answering.  ... 
doi:10.18653/v1/n18-1115 dblp:conf/naacl/TranLHZBB18 fatcat:7q2qgaecofhetdznmlaui3awd4

How Do Technology-Enhanced Learning Tools Support Critical Thinking?

Nguyen-Thinh Le
2019 Frontiers in Education  
Le and Huse (2016) developed a conversational agent that plays the role of a moderator for a group discussion.  ...  The evaluation study of the Socratic conversational agent (Le and Huse, 2016) reported encouraging results that the Socratic group discussion moderated by a conversational agent has the tendency to activate  ... 
doi:10.3389/feduc.2019.00126 fatcat:x4qvek2sxrbvrbjiqfvzwerhzq

Conceptualization of an AI Based Assistant to Support the Compatibility of Family and Paid Work

Philippe Krajsic, Martin Schieck, Ingolf Römer, Silvia Torres Landaverde, Carsta Militzer-Horstmann, Bogdan Franczyk
2020 Communication Papers of the 2020 Federated Conference on Computer Science and Information Systems  
Essentially, we provide a framework and starting point for research, development, and evaluation of an AI-based chatbot for the reconciliation of paid work and family.  ...  We are developing a conceptual reference model of proven methods and technologies for the generation of information that can be queried by interested parties via an bot service, thus simplifying professional  ...  goals, conversational history, and current state of the agent's understanding; 5) general knowledge that the agent should have about external world in order to efficiently exploit contextual information  ... 
doi:10.15439/2020f45 dblp:conf/fedcsis/KrajsicSRLMF20 fatcat:zwmozjmwwrbfxhhnhfvtoofptm

"It doesn't matter what you are!" Explaining social effects of agents and avatars

Astrid M. von der Pütten, Nicole C. Krämer, Jonathan Gratch, Sin-Hwa Kang
2010 Computers in Human Behavior  
We used a 2 Â 2 design with two levels of agency (agent or avatar) and two levels of behavioral realism (showing feedback behavior versus showing no behavior).  ...  Empirical studies have repeatedly shown that autonomous artificial entities, so-called embodied conversational agents, elicit social behavior on the part of the human interlocutor.  ...  Please only respond to the questions and do not ask questions yourself, because the other participant is instructed not to answer.  ... 
doi:10.1016/j.chb.2010.06.012 fatcat:2o3pjfsiqndunj7oduai6n6rze

Talking Topically to Artificial Dialog Partners: Emulating Humanlike Topic Awareness in a Virtual Agent [chapter]

Alexa Breuing, Ipke Wachsmuth
2013 Communications in Computer and Information Science  
This paper presents how to enable topically coherent conversations between humans and interactive systems by emulating humanlike topic awareness in the virtual agent Max.  ...  Therefore, we firstly realized automatic topic detection and tracking on the basis of contextual knowledge provided by Wikipedia and secondly adapted the agent's conversational behavior by means of the  ...  We thank Birgit Endrass and Elisabeth André from the University of Augsburg for providing parts of their CUBE-G corpus.  ... 
doi:10.1007/978-3-642-36907-0_26 fatcat:tcf3ldrgk5cmteq2c3dyxhdb3e

Research in the supporting sciences

1982 Language Teaching  
An effective metaphor has heuristic power, suggesting new connections and novel courses of action. 82-211 Manor, Ruth. A language for questions and answers.  ...  propositions, ask questions and answer them.  ... 
doi:10.1017/s0261444800009459 fatcat:g2ytptr36vcyxaywheud27bkxa

Chatbots for learning: A review of educational chatbots for the Facebook Messenger

Pavel Smutny, Petra Schreiberova
2020 Computers & Education  
A B S T R A C T With the exponential growth in the mobile device market over the last decade, chatbots are becoming an increasingly popular option to interact with users, and their popularity and adoption  ...  The findings provide tips for teachers to integrate chatbots into classroom practice and advice what types of chatbots they can try out.  ...  Ministry of Education, Youth and Sports, Czechia.  ... 
doi:10.1016/j.compedu.2020.103862 fatcat:p5f54lxcovdv3i63n7me6xpmyq

Usefulness, localizability, humanness, and language-benefit: additional evaluation criteria for natural language dialogue systems

Bayan AbuShawar, Eric Atwell
2016 International Journal of Speech Technology  
Human-computer dialogue systems interact with human users using natural language.  ...  We present some of the different evaluation techniques used in natural language dialogue systems, including black box and glass box, comparative, quantitative, and qualitative evaluation.  ...  information over the telephone about train connections between 1200 German cities (Aust, Oerder, Seide, and Steinbiss, 1995) .  ... 
doi:10.1007/s10772-015-9330-4 fatcat:o3gpxewrl5arfnmkctsjlv5b5u

Diagnosing Language Variations: Underlying Principles for Syntactic Assessment

Thomas Roeper
2004 Seminars in Speech and Language  
The item types proposed for this purpose encompass wh-questions, passives, and articles, and test the child's understanding of implicit grammatical relations, the rules governing syntactic movement, and  ...  We present the rationale for the items and the specific research supporting them, as well as some suggestions for how to help children who fail on the concepts to gain a better understanding of them.  ...  Sets For the child who does not understand the need to answer with a set, we can imply the multiple nature of wh-words through other lexical and contextual support.  ... 
doi:10.1055/s-2004-824825 pmid:15088232 fatcat:grhpt3aw4bgudjsy7eq255gyby

Spoken dialogue technology: enabling the conversational user interface

Michael F. McTear
2002 ACM Computing Surveys  
Spoken dialogue systems allow users to interact with computer-based applications such as databases and expert systems by using natural spoken language.  ...  , reviews some currently available dialogue development toolkits, and outlines prospects for future development.  ...  Ronnie Smith, David James, and Ian O'Neill, and from the anonymous reviewers of the paper.  ... 
doi:10.1145/505282.505285 fatcat:56666shnuja5xiy3kju3v2kgbq

Search as Learning (Dagstuhl Seminar 17092)

Kevyn Collins-Thompson, Preben Hansen, Claudia Hauff, Marc Herbstritt
2017 Dagstuhl Reports  
The 3-day seminar started with four perspective talks, providing four different views on the topic of search as learning: interactive information retrieval (IR), psychology, education and system-oriented  ...  The motivation for the seminar stems from the fact that modern Web search engines are largely engineered and optimized to fulfill lookup tasks instead of complex search tasks.  ...  How should a conversational agent (presumably trained automatically on vast quantities of text) deal with questions to which no clear consensus answer exist ("Does God exist")? 2.  ... 
doi:10.4230/dagrep.7.2.135 dblp:journals/dagstuhl-reports/Collins-Thompson17 fatcat:4lxrrultkjac7elptw2mazwgci
« Previous Showing results 1 — 15 out of 20,349 results