Incremental Information State Updates in an Obligation-Driven Dialogue Model

Kreutel, Jörn; Matheson, Colin

doi:10.1093/jigpal/11.4.485

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Elaborations have been made for typical situations in information-seeking and task-oriented dialogs, including grounding and obligations, such as Matheson et al (2000), and Kreutel & Matheson (2003). Altogether, information state-based techniques regulate locally possible dialog continuations, as well as some overarching contextual factors.…”

Section: Linguistic Modelsmentioning

confidence: 99%

Automated Generation of User Interfaces – A Comparison of Models and Future Prospects

Horacek¹,

Popp²,

Raneburger³

2012

Human Machine Interaction - Getting Closer

View full text Add to dashboard Cite

Section: Linguistic Modelsmentioning

confidence: 99%

Automated Generation of User Interfaces – A Comparison of Models and Future Prospects

Horacek¹,

Popp²,

Raneburger³

2012

Human Machine Interaction - Getting Closer

View full text Add to dashboard Cite

“…Approaches pursued typically address certain text sorts or phenomena such as some classes of speech acts, in abstract semantics. Elaborations have been made for typical situations in information-seeking and task-oriented dialogs, including grounding and obligations [8,13]. Table 1.…”

Section: The Model Based On the Information State Approachmentioning

confidence: 99%

Real-Time News Event Extraction for Global Crisis Monitoring

Tanev¹,

Piskorski²,

Atkinson³

Lecture Notes in Computer Science

View full text Add to dashboard Cite

. It also contains some of the best research proposals as submitted to the NLDB 2008 doctoral symposium held on June 24, 2008. The programme also includes three invited talks covering the main perspectives of the application of natural language to information systems: the way humans process, communicate and understand natural language, what are the implications and challenges towards semantic search for the new Web generation, how natural language applies to the well-established database way of querying as a means to unlock data and information for end users.We received 68 papers as regular papers for the main conference and 14 short papers for the doctoral symposium. Each paper for the main conference was assigned four reviewers based on the preferences expressed by the Program Committee members. We ensured that every paper had at least two reviewers that expressed interest in reviewing it or indicated that they could review it. We ensured that each paper got at least three reviews. As a result, only 10% of the papers were reviewed by three reviewers.The Conference Chair and the two Program Committee Co-chairs acted as Meta-Reviewers. Each of them took roughly 1/3 of the papers (obviously respecting conflicts of interest), for which s/he was responsible. This included studying the reviews, launching discussions and asking for clarifications whenever necessary, as well as studying the papers whenever a need for an informed additional opinion arose or when the reviewers' notes did not allow for a decision.After the review deadline, each meta-reviewer went through the reviews of their papers and made a preliminary assessment. To the extent possible, the meta-reviewers tried to get the inconsistencies and discrepancies resolved. We used a ranking list as resulted from the weighted average scores of all papers in a scale from 1 (lowest possible) to 6 (highest possible) as computed by taking into account the reviewer's confidence as a weighting factor. The final acceptance rate counting the number of full papers according to the NLDB tradition, at least during the last three years, was 29.4%. The following decision rules were used to make the final decisions:-Full Papers: Papers with a weighted average score of 4.0 (weak accept) or more were accepted as full papers. There were 17 such papers. One more paper was subject to conditional acceptance. This gave us room for two more papers to be accepted as full papers. We considered the papers with a weighted average score of 3.8 or above but less than 4.0 to select the two papers. Taking into account the reviewer feedback and the scores, we decided to select two papers with the least number of negative (1.0, 2.0 or 3.0) scores. -Short Papers: Papers with a weighted average score of 3.7 or above but less than 4.0 were accepted as short papers. VI Preface-Posters: Papers with a weighted average score of 3.0 (weak reject) or above but less than 3.7 were accepted as posters. -Doctoral Symposium Papers: The four-page long papers, which were invited from the submissions to the ...

show abstract

An Abstract Model of Man-Machine Interaction Based on Concepts from NL Dialog Processing

Horacek

2006

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

Incremental Information State Updates in an Obligation-Driven Dialogue Model

Cited by 5 publications

References 9 publications

Automated Generation of User Interfaces – A Comparison of Models and Future Prospects

Automated Generation of User Interfaces – A Comparison of Models and Future Prospects

Real-Time News Event Extraction for Global Crisis Monitoring

An Abstract Model of Man-Machine Interaction Based on Concepts from NL Dialog Processing

Contact Info

Product

Resources

About