Publication Year: 2013
DOI: https://doi.org/10.1109/jproc.2012.2225812
Abstract: Statistical dialog a art in the development of POMDP-based spoken dialog systems. data-driven framework that reduces the cost of laboriously handcrafting systems complex dialog managers and that provides robustness against the errors (SDSs) created by speech recognizers operating in noisy environments. By including are an explicit Bayesian model of uncertainty Show more
Authors:
Publication Year: 1989
DOI: DOI not available
Abstract: User models field the field of user modeling. Most of the prominent international of researchers in this area have contributed to this volume. Their artificial papers are grouped into four sections: The introductory section contains intelligence a general view of the field as a whole, and dialog a number of Show more
Authors:
Publication Year: 2006
DOI: https://doi.org/10.1016/j.csl.2006.06.008
Abstract: Not available
Authors:
Publication Year: 1977
DOI: https://doi.org/10.1016/0004-3702(77)90018-2
Abstract: Not available
Authors:
Publication Year: 2020
DOI: https://doi.org/10.1145/3383123
Abstract: There is systems also identify users’ emotional and social needs during the conversation. due Consistency requires the system to demonstrate a consistent personality to to win users’ trust and gain their long-term confidence. Interactiveness refers the to the system’s ability to generate interpersonal responses to achieve availability particular social goals Show more
Authors:
Publication Year: 2005
DOI: https://doi.org/10.21437/interspeech.2005-399
Abstract: In this system was made available to the general public. The Let’s paper, Go Public spoken dialog system provides bus schedule information to we the Pittsburgh population during off-peak times. This paper describes the describe changes necessary to make the system usable for the general how public and presents analysis Show more
Authors:
Publication Year: 2018
DOI: https://doi.org/10.18653/v1/p18-1136
Abstract: End-to-end task-oriented incorporating on three different task-oriented dialog datasets. knowledge bases. In this paper, we propose a novel dialog yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address systems this issue. Mem2Seq is the first neural generative model that usually combines the multi-hop attention over memories with the idea Show more
Authors:
Publication Year: 2006
DOI: https://doi.org/10.1016/j.jbi.2005.12.004
Abstract: Not available
Authors:
Publication Year: 1989
DOI: https://doi.org/10.1007/978-3-642-83230-7_1
Abstract: Not available
Authors:
Publication Year: 2004
DOI: https://doi.org/10.3115/1218955.1218966
Abstract: A challenging of utterance generation modules that are fast, flexible and general, problem yet produce high quality output in particular domains. A promising for approach is trainable generation, which uses general-purpose linguistic knowledge automatically spoken adapted to the application domain. This paper presents a trainable dialog sentence planner for the Show more
Authors:
Publication Year: 1989
DOI: https://doi.org/10.1007/978-3-642-83230-7
Abstract: Not available
Authors:
Publication Year: 1995
DOI: https://doi.org/10.1093/oso/9780195091878.001.0001
Abstract: As spoken great in-depth result from pertinent experiments. Researchers and professionals in natural strides, language systems will find this important new book an invaluable numerous addition to their libraries. issues regarding dialog processing still need to natural be resolved. This book presents an exciting new dialog processing language architecture that Show more
Authors:
Publication Year: 2018
DOI: https://doi.org/10.1609/aaai.v32i1.11321
Abstract: Open-domain human-computer past on both retrieval and generative dialog systems show that RUBER few has a high correlation with human annotation, and that RUBER years. has fair transferability over different datasets. However, there does not exist a standard conversation automatic evaluation metric for open-domain dialog systems; researchers usually resort has Show more
Authors:
Publication Year: 2019
DOI: https://doi.org/10.18653/v1/d19-1189
Abstract: Qibin Chen, Hongxia Yang, Jie Tang. Proceedings of the 2019 Conference on Junyang Empirical Methods in Natural Language Processing and the 9th International Lin, Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019. Yichang Zhang, Ming Ding, Yukuo Cen,
Authors:
Publication Year: 2019
DOI: https://doi.org/10.24963/ijcai.2019/706
Abstract: End-to-end neural problem utterances and responses, and it ensures the appropriate selection of of knowledge during the training process. Meanwhile, a prior distribution, which generating is inferred from utterances only, is used to approximate the uninformative posterior distribution so that appropriate knowledge can be selected even responses. without responses during Show more
Authors:
Found 292780 results in 0.409 seconds
Including any of the words AND
, OR
, or NOT
in any of your searches will enable
boolean search. Those words must be UPPERCASE. You can use this in all searches, including using
the search parameter, and using search filters.
This allows you to craft complex queries using those boolean operators along with parentheses and quotation marks.
Surrounding a phrase with quotation marks will search for an exact match of that phrase, after stemming and
stop-word removal (be sure to use double quotation marks — "
). Using parentheses will specify order of
operations for the boolean operators. Words that are not separated by one of the boolean operators will be
interpreted as AND
.
Behind the scenes, the boolean search is using Elasticsearch's query string query on the searchable fields (such as
title, abstract, and fulltext for works; see each individual entity page for specifics about that entity). Wildcard
and fuzzy searches using *
, ?
or ~
are not allowed; these characters will be
removed from any searches. These searches, even when using quotation marks, will go through the same cleaning as
described above, including stemming and removal of stop words.
Search for works that mention "elmo"
and "sesame street"
, but not the words
"cookie"
or "monster"
:
"elmo" AND "sesame street" NOT "cookie" NOT "monster"