Filters








65,956 Hits in 2.3 sec

Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset

Bill Byrne, Karthik Krishnamoorthi, Chinnadhurai Sankar, Arvind Neelakantan, Ben Goodrich, Daniel Duckworth, Semih Yavuz, Amit Dubey, Kyu-Young Kim, Andy Cedilnik
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)  
Dialogs are labeled with API calls and arguments, a simple and cost effective approach which avoids the requirement of complex annotation schema.  ...  The layer of abstraction between the dialog model and the service provider API allows for a given model to interact with multiple services that provide similar functionally.  ...  Two-person, spoken dataset In order to replicate a two-participant, automated digital assistant experience, we built a WOz platform that pairs agents playing the digital assistant with crowdsourced workers  ... 
doi:10.18653/v1/d19-1459 dblp:conf/emnlp/ByrneKSNGDYDKC19 fatcat:lklnyxips5awnkw6q5uxwgtyiq

Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset [article]

Bill Byrne, Karthik Krishnamoorthi, Chinnadhurai Sankar, Arvind Neelakantan, Daniel Duckworth, Semih Yavuz, Ben Goodrich, Amit Dubey, Andy Cedilnik, Kyu-Young Kim
2019 arXiv   pre-print
The first involves a two-person, spoken "Wizard of Oz" (WOz) approach in which trained agents and crowdsourced workers interact to complete the task while the second is "self-dialog" in which crowdsourced  ...  Dialogs are labeled with API calls and arguments, a simple and cost effective approach which avoids the requirement of complex annotation schema.  ...  Two-person, spoken dataset In order to replicate a two-participant, automated digital assistant experience, we built a WOz platform that pairs agents playing the digital assistant with crowdsourced workers  ... 
arXiv:1909.05358v1 fatcat:fvvsjrgaarhkjg6kuyeroym7hi

Building the next generation of personal digital Assistants

P. Milhorat, S. Schlogl, G. Chollet, J. Boudy, A. Esposito, G. Pelosi
2014 2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)  
Yet, despite their promise of being context-aware and adapted to a user's preferences and very distinct needs, truly personal assistants are still missing.  ...  In this paper we highlight some of the challenges in building personalized speech-operated assistive technology and propose a number of research and development directions we have undertaken in order to  ...  PERSONAL DIGITAL ASSISTANTS Our common understanding of a personal assistant is that of a person (or an agent) who is able to provide distinct help at a given time and in a given activity context.  ... 
doi:10.1109/atsip.2014.6834655 dblp:conf/atsip/MilhoratSCBEP14 fatcat:enognztjrnepbny6kbkvqj3gcy

Mixed-initiative Personal Assistants

Joshua W. Buck, Saverio Perugini
2017 Proceedings of the 2017 ACM SIGCSE Technical Symposium on Computer Science Education - SIGCSE '17  
Our toolkit can automatically operationalize a dialog that involves multiple prompts and/or sub-dialogs, given a highlevel dialog specification of it.  ...  Our current research entails incorporating the use of natural language to make the flexibility in communicating user utterances commensurate with that in dialog completion paths.  ...  and widespread adoption of personal assistant technologies.  ... 
doi:10.1145/3017680.3022455 dblp:conf/sigcse/BuckP17 fatcat:anokwh6x6vfjzlpezirnztkwwm

Personalization of Conversational Agents in Healthcare: A Systematic Review (Preprint)

Ahmet Baki Kocaballi, Shlomo Berkovsky, Juan C Quiroz, Liliana Laranjo, Huong Ly Tong, Fahimeh Rezazadegan, Agustina Briatore, Enrico Coiera
2019 Journal of Medical Internet Research  
The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact.  ...  Future research could incorporate personalization as a distinct design factor with a more careful consideration of its impact on health outcomes and its implications on patient safety, privacy, and decision-making  ...  Conducted in April 2017 and updated in March 2019 "Conversational agent*" OR "conversational system*" OR "dialog system*" OR "dialogue system*" OR "assistance technology" OR "assistance technologies" OR  ... 
doi:10.2196/15360 pmid:31697237 pmcid:PMC6873147 fatcat:lw74qc72ubhj5kkadtqzje6jiy

Migratable AI: Personalizing Dialog Conversations with migration context [article]

Ravi Tejwani, Boris Katz, Cynthia Breazeal
2020 arXiv   pre-print
We collected a dataset from the dialog conversations between crowdsourced workers with the migration context involving personal and non-personal utterances in different settings (public or private) of  ...  However, these migratable agents lack contextual understanding of the user information and the migrated device during the dialog conversations with the user.  ...  At the end of each dialog conversation, the AMT workers were instructed to label each utterance in the dialog with "NP" for non-personal information and "P" for personal information.  ... 
arXiv:2010.12091v1 fatcat:wxauteim2fcfbknh4smzncxcya

Preferences for single-turn vs. multi-turn voice dialogs in automotive use cases – results of an interactive user survey in Germany

P. Burggraf, M. Beyer, J.P. Ganser, T. Adlon, K. Muller, C. Riess, K. Zollner, T. Sabmannshausen, V. Kammerer
2022 IEEE Access  
Furthermore, BMW introduced its AI-supported voice dialog system in 2018, the so-called BMW "Intelligent Personal Assistant".  ...  With the development of Siri in 2010 and other intelligent personal assistants, the technology has been rolled out for mass production in smart devices.  ...  The upcoming challenge here is to align voice assistants with conversation dialog types (multi-turn vs. single-turn) and future use cases required in the automotive context.  ... 
doi:10.1109/access.2022.3174592 fatcat:ccrssvfiazf3rnxphluhrv4bvm

Preferences for Single-Turn vs. Multiturn Voice Dialogs in Automotive Use Cases : Results of an Interactive User Survey in Germany

Peter Burggräf, Moritz Beyer, Jan-Philip Ganser, Tobias Adlon, Katharina Maria Müller, Constantin Riess, Kaspar Zollner, Till Sabmannshausen, Vincent Kammerer
2022 IEEE access 10  
of the voice modality as a direct function should be considered.  ...  Voice assistants have manifested their existence in the vehicle over the last decade.  ...  Furthermore, BMW introduced its AI-supported voice dialog system in 2018, the so-called BMW ''Intelligent Personal Assistant''.  ... 
doi:10.18154/rwth-2022-06449 fatcat:fljkbz2nsnfcdowgquht4qwggq

DeRool: A rule-based dialog engine

Kevin Angele, Jürgen Angele
2020 International Web Rule Symposium  
In real life, a dialog between humans is an ongoing change of the dialog initiative between the persons talking to each other.  ...  To enable a more natural communication between users and assistants, we present DeRool, a rule-based dialog engine that is able to handle complex dialogs.  ...  The user asks a question, and the digital assistant returns an answer. The idea is that a conversation with a virtual digital assistant becomes more natural, like talking to a real person.  ... 
dblp:conf/ruleml/AngeleA20 fatcat:eybss3lofbajpgzdirmjtsu4zq

Navigation Dialog of Blind People: Recovery from Getting Lost

Jan Vystrcil, Ivo Maly, Jan Balata, Zdenek Mikovec
2014 Proceedings of the EACL 2014 Workshop on Dialogue in Motion  
In this paper we focus on qualitative analysis of dialogs between lost blind person and navigator, which is done through the mobile phone.  ...  The analysis revealed several areas where the dialog model must focus on detailed information, like evaluation of instructions provided by blind person and his/her ability to reliably locate navigation  ...  Our intention is to extend such a center in a way that the helping person will be replaced by natural language based dialog system.  ... 
doi:10.3115/v1/w14-0210 dblp:conf/eacl/VystrcilMBM14 fatcat:s4nxbpuilnfqbhwuvdz6rtbxu4

Towards Personalized Dialog Policies for Conversational Skill Discovery [article]

Maryam Fazel-Zarandi, Sampat Biswas, Ryan Summers, Ahmed Elmalt, Andy McCraw, Michael McPhilips, John Peach
2019 arXiv   pre-print
In this paper, we focus on conversational skill discovery and present a conversational agent which engages in a dialog with users to help them find the skills that fulfill their needs.  ...  To this end, we start with a rule-based agent and improve it by using reinforcement learning.  ...  This highlights the difficulty of authoring personalized dialog policies with rules, and shows the advantage of using RL for this problem.  ... 
arXiv:1911.06747v1 fatcat:ei5snfwjmrhjbcnykapew2qkli

Conversational Re-Prompting in Natural Language Dialog

Harry E. Blanchard, Osamuyimen T. Stewart
2004 Proceedings of the Human Factors and Ergonomics Society Annual Meeting  
resolutions that are Desired = specific request Undesired = vague, or ask for a person Comparison 1: Requests for a person Final Resolution = ask for a person (Asks for a person on first and second turn  ...  "I have a problem with my bill." First turn: Welcome to <service name>. I am an automated assistant. You can speak naturally to me. How may I help you?  ...  prompt Re-prompt with more specific information about types of requests Increased success rate Did not sacrifice conversational nature and naturalness of dialog Can use partial information from user's  ... 
doi:10.1177/154193120404800401 fatcat:wqjsejlbmra6deyv3g5oaso5oq

Consumer decisions with artificially intelligent voice assistants

Benedict G. C. Dellaert, Suzanne B. Shu, Theo A. Arentze, Tom Baker, Kristin Diehl, Bas Donkers, Nathanael J. Fast, Gerald Häubl, Heidi Johnson, Uma R. Karmarkar, Harmen Oppewal, Bernd H. Schmitt (+3 others)
2020 Marketing letters  
AIVAs now handle many different everyday tasks and are also increasingly assisting consumers with purchasing decisions, making AIVAs a rich topic for marketing researchers.  ...  Consumer models Artificially Intelligent interactive Voice Assistants (AIVAs), also known as Voice-Activated Personal Assistants or Smart-Home Personal Assistants, have become widely adopted by consumers  ...  Consumer adoption of AI-powered voice assistants Choosing by holding a dialog with an AIVA may involve several trade-offs between autonomy and efficiency that are not inherent in choosing with a traditional  ... 
doi:10.1007/s11002-020-09537-5 fatcat:icot6mfipjbunart2ihp7zqmb4

A Knowledge-Based Framework for the Rapid Development of Conversational Recommenders [chapter]

Dietmar Jannach, Gerold Kreutler
2004 Lecture Notes in Computer Science  
In the system, both the recommendation logic and the knowledge required for constructing the personalized dialog and adaptive web pages is contained in a declarative knowledge-base.  ...  Web-based sales assistance systems are a valuable means to guide online customers in the decision-making and product selection process.  ...  In order to be of real value, such systems have to simulate the behavior of a human sales assistant, i.e., elicit the customer's needs and preferences in a personal dialog ( [1] , [2] ) and come up with  ... 
doi:10.1007/978-3-540-30480-7_40 fatcat:7dymtzifrrhuhb4gelsmpxjiji

Wizard of Oz Method for Learning Dialog Agents [chapter]

Masayuki Okamoto, Yeonsoo Yang, Toru Ishida
2001 Lecture Notes in Computer Science  
This paper describes a framework to construct interface agents with example dialogs based on the tasks by the machine learning technology.  ...  The Wizard of Oz method is used to collect example dialogs, and a finite state machine-based model is used for the dialog model.  ...  by the New Energy and Industrial Technology Development Organization for Senior Support System Project, by the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Scientific Research (A)  ... 
doi:10.1007/3-540-44799-7_3 fatcat:u5zuyg3ynzehvbskovumkja5xy
« Previous Showing results 1 — 15 out of 65,956 results