Filters








1,086 Hits in 5.0 sec

User modelling, dialog structure, and dialog strategy in HAM-ANS

Katharina Morik
1985 Proceedings of the second conference on European chapter of the Association for Computational Linguistics -   unpublished
-structuring dialog -understanding and generating a wider range of speech acts than simply information request and answer user modelling User modelling in HAM-ANS is closely connected to dialog structure  ...  In advising the user, the system generates and verbalizes speech acts. The choice of the speech act is guided by the user profile and the dialog strategy of the system.  ...  This paper does not evaluate the overall HAM-ANS but is restricted to the aspect of dialog structuring and user modelling.  ... 
doi:10.3115/976931.976971 fatcat:4h5r2atum5c23ajkvjkggydtsy

User Models in Dialog Systems [chapter]

Wolfgang Wahlster, Alfred Kobsa
1989 User Models in Dialog Systems  
Research within and outside of artificial intelligence which is related to user modeling in dialog systems is discussed.  ...  Although the survey is restricted to user models in naturallanguage dialog systems, most of the concepts and methods discussed can be extended to AI dialog systems in general.  ...  Anticipation Feedback A special case of exploitation of a user model (which is realized in dialog systems like HAM-ANS, NAOS and IMP) is its use in various forms of anticipation feedback loops.  ... 
doi:10.1007/978-3-642-83230-7_1 fatcat:d2ma2ui6ofbcdom64qxpou3u54

Dialogue-based user models

W. Wahlster, A. Kobsa
1986 Proceedings of the IEEE  
The paper investigates several approaches to user modeling in natural-language dialog systems.  ...  Then, techniques for constructing user models in the course of a dialog are presented and recent proposals for representing a wide range of assumptions about a user's beliefs and goals in a system's knowledge  ...  Jameson and an anonymous referee for their comments on an earlier version of this paper.  ... 
doi:10.1109/proc.1986.13574 fatcat:7wxtm5uzbje3jjlshdudzfuosy

Mixed-initiative in human augmented mapping

J. Peltason, F.H.K. Siepmann, T.P. Spexard, B. Wrede, M. Hanheide, E.A. Topp
2009 2009 IEEE International Conference on Robotics and Automation  
In this paper we discuss a mixed initiative strategy for robotic learning by interacting with a user in a joint map acquisition process.  ...  In scenarios that require a close collaboration and knowledge transfer between inexperienced users and robots, the "learning by interacting" paradigm goes hand in hand with appropriate representations  ...  "Cognitive Interaction Techology" (CITEC), and the German Service Robotic Initiative (DE-SIRE).  ... 
doi:10.1109/robot.2009.5152683 dblp:conf/icra/PeltasonSSWHT09 fatcat:prhf27y2d5dybmjmhrzhqa4w3e

A SPOKEN DIALOG SYSTEM WITH AUTOMATIC RECOVERY MECHANISM FROM MISRECOGNITION

Norihide Kitaoka, Hirotoshi Yano, Seiichi Nakagawa
2006 2006 IEEE Spoken Language Technology Workshop  
As for a dialog strategy, we introduced a new criterion based on 'efficiency for convergence' and 'consistency with understanding hypotheses' to select an appropriate system response.  ...  We developed a spoken dialog system using these techniques and showed some dialog examples in which misrecognition was naturally corrected.  ...  An example of a dialog. Dialog example Examples of the dialogs with the system are shown in Figure 3 . The user utterance, recognition results, and understanding hypotheses are shown separately.  ... 
doi:10.1109/slt.2006.326790 dblp:conf/slt/KitaokaYN06 fatcat:ypbzlfh22ben5icqlgbhckmbxa

Attentive History Selection for Conversational Question Answering

Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, W. Bruce Croft, Mohit Iyyer
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
We show that position information plays an important role in conversation history modeling. We also visualize the history attention and provide new insights into conversation history understanding.  ...  Third, in addition to handling conversation history, we take advantage of multi-task learning (MTL) to do answer prediction along with another essential conversation task (dialog act prediction) using  ...  ACKNOWLEDGMENTS This work was supported in part by the Center for Intelligent Information Retrieval and in part by NSF IIS-1715095.  ... 
doi:10.1145/3357384.3357905 dblp:conf/cikm/QuYQZCCI19 fatcat:hptk7biqozagvkvf2m2e2u4pjy

A speech understanding and dialog system with a homogeneous linguistic knowledge base

M. Mast, F. Kummert, U. Ehrlich, G.A. Fink, T. Kuhn, H. Niemann, G. Sagerer
1994 IEEE Transactions on Pattern Analysis and Machine Intelligence  
To enforce a more model driven strategy neither a left to right nor an island driven strategy is used.  ...  To enable the system to communicate in a spoken dialog with the user, and not only to answer questions like in a question-answer system a dialog component and also an answer generating component are needed  ...  and coeditor of another book on knowledge representation for image understanding and on the architecture of speech dialog systems.  ... 
doi:10.1109/34.273733 fatcat:5ch4agpxfnhf3gofbdsvlpfdfq

A Conversational Approach to Process-oriented Case-based Reasoning

Christian Zeyen, Gilbert Müller, Ralph Bergmann
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Process-oriented case-based reasoning (POCBR) supports workflow modeling by retrieving and adapting workflows that have proved useful in the past.  ...  This paper closes this gap and presents a conversational POCBR approach (C-POCBR) in which questions related to structural properties of the workflow cases are generated automatically.  ...  In C-POCBR the users follow the dialog and investigate the presented workflow.  ... 
doi:10.24963/ijcai.2018/762 dblp:conf/ijcai/ZeyenMB18 fatcat:argpjlcn3zaqvola4jcb4ozoji

How to Win Arguments

Klaus Weber, Niklas Rach, Wolfgang Minker, Elisabeth André
2020 Datenbank-Spektrum  
pros and cons to a user on a controversial topic.  ...  To raise awareness of the different aspects of persuasion (how and what), we present a multimodal dialog system consisting of two virtual agents that use synthetic speech in a discussion setting to present  ...  For the argumentation strategy, the combination of argument structure and dialogue game in a multi-agent setup was evaluated in a user study [17] by comparing transcripts of artificial discussions with  ... 
doi:10.1007/s13222-020-00345-9 fatcat:27l4fbeyl5eqbopma5zfknl7em

Cooperative access systems

W. Wahlster
1984 Future generations computer systems  
Topics covered include user modeling, the generation of explanations, mixed initiative dialogs and knowledge acquisition via NL communication.  ...  Then we briefly review the state of the art in NL interfaces to databases and expert systems.  ...  I am, however, currently coordinating a joint project, funded by the German Ministry for Research and Technology, in which companies like Nixdorf, Siemens and SCS together with academic research groups  ... 
doi:10.1016/0167-739x(84)90031-1 fatcat:egrgt7dg25aq3l3ihcyyo6tqta

Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems [article]

Po-Nien Kung, Chung-Cheng Chang, Tse-Hsuan Yang, Hsin-Kai Hsu, Yu-Jia Liou, Yun-Nung Chen
2021 arXiv   pre-print
In this paper, we leverage multi-task learning techniques to train a GPT-2 based model on a more challenging dataset with multiple domains, multiple modalities, and more diversity in output formats.  ...  Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling.  ...  We use a pretrained GPT-2 (Radford et al. 2019 ) model with a LM head as the main structure to predict Multimodal Dialog Response Generation & Retrieval and Multimodal Dialog State Tracking (MM-DST).  ... 
arXiv:2110.05221v1 fatcat:urfigpg4lvbkhfc2c4k2jtzl3a

Conversational Machine Comprehension: a Literature Review [article]

Somil Gupta, Bhanu Pratap Singh Rawat, Hong Yu
2020 arXiv   pre-print
The rise in interest has, however, led to a flurry of concurrent publications, each with a different yet structurally similar modeling approach and an inconsistent view of the surrounding literature.  ...  Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation  ...  Choi et al. (2018) validate that this dialog-turn encoding strategy performs better in practice. 2.  ... 
arXiv:2006.00671v2 fatcat:ht77ouzpdfgirb57v664z722ke

GKS: Graph-based Knowledge Selector for Task-oriented Dialog System [article]

Jen-Chieh Yang, Jia-Yan Wu, Sung-Ping Chang, Ya-Chieh Huang
2021 arXiv   pre-print
In the Tenth Dialog System Technology Challenges (DSTC10), we participated in the second Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations.  ...  As a result, GKS outperforms several SOTA models proposed in the data-set on knowledge selection from the Ninth Dialog System Technology Challenges (DSTC9).  ...  Traditionally, TF-IDF technique (Ramos 2003) and language model are applied on similar tasks. As mentioned above, the limitations of previous works lie in the model structure.  ... 
arXiv:2112.03719v2 fatcat:h6zon3drxbhg3mtkbzkyvvma6a

NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment [article]

Julia Kiseleva, Ziming Li, Mohammad Aliannejadi, Shrestha Mohanty, Maartje ter Hoeve, Mikhail Burtsev, Alexey Skrynnik, Artem Zholus, Aleksandr Panov, Kavya Srinet, Arthur Szlam, Yuxuan Sun (+3 others)
2021 arXiv   pre-print
To facilitate research in this direction, we propose IGLU: Interactive Grounded Language Understanding in a Collaborative Environment.  ...  Human intelligence has the remarkable ability to adapt to new tasks and environments quickly.  ...  The world state representations take into account the Hamming distance between the target structure and built structure and it also tells how the target structure can be constructed successfully given  ... 
arXiv:2110.06536v2 fatcat:jyyjlgbmpbdtjf6ctqssl2xpf4

Page 77 of Computational Linguistics Vol. 14, Issue 3 [page]

1988 Computational Linguistics  
.; and Marburger, H. 1984 Talking it Over: The Natural Dialog System HAM-ANS. Technical Report ANS- 26, Research Unit for Information Science and Artificial Intelli- gence, University of Hamburg, W.  ...  on the information contained in user model.  ... 
« Previous Showing results 1 — 15 out of 1,086 results