FLoReS: A Forward Looking, Reward Seeking, Dialogue Manager

Morbini, Fabrizio; DeVault, David; Sagae, Kenji; Gerten, Jillian; Nazarian, Angela; Traum, David

doi:10.1007/978-1-4614-8280-2_28

Cited by 31 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, in the dialogue below, apart from the fact that I+S cannot represent utterance (1), question ( 2) is answered with a subdialogue starting at question (3) that shifts the dialogue initiative (Bohus and Rudnicky, 2002;Horvitz, 2007;Litman and Allen, 1987;Morbini et al, 2012). In utterances ( 4) and ( 6), the system is proposing a value and in ( 5) and ( 7), the user is rejecting or accepting the proposal.…”

Section: Mixed Initiative and Collaborationmentioning

confidence: 99%

Foundations of Collaborative Task-Oriented Dialogue: What’s in a Slot?

Cohen¹

2019

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

In this paper, we examine the foundations of task-oriented dialogues, in which systems are requested to perform tasks for humans. We argue that the way this dialogue task has been framed has limited its applicability to processing simple requests with atomic "slot-fillers". However, such dialogues can contain more complex utterances. Furthermore, situations for which it would be desirable to build task-oriented dialogue systems, e.g., to engage in collaborative or multiparty dialogues, will require a more general approach. In order to provide such an approach, we give a logical analysis of the "intent+slot" dialogue setting that overcomes these limitations.

show abstract

Section: Mixed Initiative and Collaborationmentioning

confidence: 99%

Foundations of Collaborative Task-Oriented Dialogue: What’s in a Slot?

Cohen¹

2019

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

show abstract

“…The study used 4 trained Natural Language Understanding (NLU) classifiers, each of which: identifies generic dialogue act types, assigns positive or negative valence to the user input, supports domain-specific small talk, and identifies domain-specific dialogue acts. The dialogue policy the study implemented used the FloReS (3) dialogue manager. The researchers conducted an experiment and the results showed that the users were comfortable in sharing information with SimSensei, giving the impression that virtual human agent are effective in extracting information from its users.…”

Section: + Both Authors Have Equal Contributionmentioning

confidence: 99%

Automatic Curriculum Vitae Creator Using a Virtual Human Speech Interviewer

Molon¹,

Famador²

2016

Proceedings of the 4th IIAE International Conference on Intelligent Systems and Image Processing 2016

View full text Add to dashboard Cite

IntroductionAn application that takes in speech, analyzes it, and turns it into a Curriculum Vitae is an innovative approach. This study aims to create such application using text-to-speech, speech recognition, and natural language processing. The user is asked about his/her personal and educational background in an orderly manner using a text-to-speech module. The order of the questions depends on the format of the Curriculum Vitae.With the SpeechRecognition python library, the user's speech input is captured and converted into text which will be further processed and analyzed. Word tokenization is used to divide a sentence into list of words. Each element in this list of words is labeled with their corresponding part-of-speech tag. These tagged words will then make it easier for the program to identify the actual user input, which will be written in a Word or LibreOffice document (.docx, .doc, .odt) using the pythondocx library. Using this approach, the study was successful in creating such application. Speech-to-text, speech recognition, and natural language processing can be integrated to create a virtual human interviewer capable of conversing with the user to create a Curriculum Vitae. Although the tools used proved to be very effective and efficient, the python-docx library does not provide a tool for editing written text in the event of the user giving a wrong input, creating an area for future research.Keywords: speech recognition, natural language processing, Curriculum Vitae, virtual human agent.+ Both authors have equal contribution.Handsfree technology is popular nowadays for its convenience. People are becoming more comfortable in talking to their devices in order for it to do certain tasks. Speech recognition and natural language processing can be integrated to create an application capable of understanding and interacting with its users. The Virtual Human Toolkit (1) made it possible for an easy production and development of virtual human agents that interacts with users. This study integrated different aspects of human-to-human interaction, which includes: speech recognition, natural language understanding, nonverbal behavior understanding, natural language generation, and nonverbal behavior generation. The addition of nonverbal behavior understanding and generation enhances the face-to-face interaction between human and computer.This study is significant because it aims to shorten the time of filling up a Curriculum Vitae. Speaking, instead of writing, would make the process faster. Also, due to the limitation of the Speech Recognition software, words must be properly uttered for the System to rightly detect the input speech. As a result, non-native English speakers will have a chance to practice how to pronounce the words correctly. Another significance of this study is to create a framework for an automated speech to text form filler. This framework promotes more possibilities for future research.An example of an application that interacts with humans is SimSensei (2) which engages i...

show abstract

“…For natural language understanding, generation, and dialogue management, we built on top of the FLoRes system (Morbini et al 2012). This system allowed us to define the information state for employees and attributes and a set of policies for prompting and responding to the user.…”

Section: Related Workmentioning

confidence: 99%