@inproceedings{gemmell-etal-2022-grillbot,
title = "{GRILLB}ot: A multi-modal conversational agent for complex real-world tasks",
author = "Gemmell, Carlos and
Rossetto, Federico and
Mackie, Iain and
Owoicho, Paul and
Fischer, Sophie and
Dalton, Jeff",
editor = "Lemon, Oliver and
Hakkani-Tur, Dilek and
Li, Junyi Jessy and
Ashrafzadeh, Arash and
Garcia, Daniel Hern{\'a}ndez and
Alikhani, Malihe and
Vandyke, David and
Du{\v{s}}ek, Ond{\v{r}}ej",
booktitle = "Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2022",
address = "Edinburgh, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sigdial-1.63",
doi = "10.18653/v1/2022.sigdial-1.63",
pages = "654--658",
abstract = "We present GRILLBot, an open-source multi-modal task-oriented voice assistant to help users perform complex tasks, focusing on the domains of cooking and home improvement. GRILLBot curates and leverages web information extraction to build coverage over a broad range of tasks for which a user can receive guidance. To represent each task, we propose TaskGraphs as a dynamic graph unifying steps, requirements, and curated domain knowledge enabling contextual question answering, and detailed explanations. Multi-modal elements play a key role in GRILLBot both helping the user navigate through the task and enriching the experience with helpful videos and images that are automatically linked throughout the task. We leverage a contextual neural semantic parser to enable flexible navigation when interacting with the system by jointly encoding stateful information with the conversation history. GRILLBot enables dynamic and adaptable task planning and assistance for complex tasks by combining elements of task representations that incorporate text and structure, combined with neural models for search, question answering, and dialogue state management. GRILLBot competed in the Alexa prize TaskBot Challenge as one of the finalists.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gemmell-etal-2022-grillbot">
<titleInfo>
<title>GRILLBot: A multi-modal conversational agent for complex real-world tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Gemmell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Rossetto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iain</namePart>
<namePart type="family">Mackie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Owoicho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Fischer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="family">Dalton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Ashrafzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="given">Hernández</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Edinburgh, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present GRILLBot, an open-source multi-modal task-oriented voice assistant to help users perform complex tasks, focusing on the domains of cooking and home improvement. GRILLBot curates and leverages web information extraction to build coverage over a broad range of tasks for which a user can receive guidance. To represent each task, we propose TaskGraphs as a dynamic graph unifying steps, requirements, and curated domain knowledge enabling contextual question answering, and detailed explanations. Multi-modal elements play a key role in GRILLBot both helping the user navigate through the task and enriching the experience with helpful videos and images that are automatically linked throughout the task. We leverage a contextual neural semantic parser to enable flexible navigation when interacting with the system by jointly encoding stateful information with the conversation history. GRILLBot enables dynamic and adaptable task planning and assistance for complex tasks by combining elements of task representations that incorporate text and structure, combined with neural models for search, question answering, and dialogue state management. GRILLBot competed in the Alexa prize TaskBot Challenge as one of the finalists.</abstract>
<identifier type="citekey">gemmell-etal-2022-grillbot</identifier>
<identifier type="doi">10.18653/v1/2022.sigdial-1.63</identifier>
<location>
<url>https://aclanthology.org/2022.sigdial-1.63</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>654</start>
<end>658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GRILLBot: A multi-modal conversational agent for complex real-world tasks
%A Gemmell, Carlos
%A Rossetto, Federico
%A Mackie, Iain
%A Owoicho, Paul
%A Fischer, Sophie
%A Dalton, Jeff
%Y Lemon, Oliver
%Y Hakkani-Tur, Dilek
%Y Li, Junyi Jessy
%Y Ashrafzadeh, Arash
%Y Garcia, Daniel Hernández
%Y Alikhani, Malihe
%Y Vandyke, David
%Y Dušek, Ondřej
%S Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2022
%8 September
%I Association for Computational Linguistics
%C Edinburgh, UK
%F gemmell-etal-2022-grillbot
%X We present GRILLBot, an open-source multi-modal task-oriented voice assistant to help users perform complex tasks, focusing on the domains of cooking and home improvement. GRILLBot curates and leverages web information extraction to build coverage over a broad range of tasks for which a user can receive guidance. To represent each task, we propose TaskGraphs as a dynamic graph unifying steps, requirements, and curated domain knowledge enabling contextual question answering, and detailed explanations. Multi-modal elements play a key role in GRILLBot both helping the user navigate through the task and enriching the experience with helpful videos and images that are automatically linked throughout the task. We leverage a contextual neural semantic parser to enable flexible navigation when interacting with the system by jointly encoding stateful information with the conversation history. GRILLBot enables dynamic and adaptable task planning and assistance for complex tasks by combining elements of task representations that incorporate text and structure, combined with neural models for search, question answering, and dialogue state management. GRILLBot competed in the Alexa prize TaskBot Challenge as one of the finalists.
%R 10.18653/v1/2022.sigdial-1.63
%U https://aclanthology.org/2022.sigdial-1.63
%U https://doi.org/10.18653/v1/2022.sigdial-1.63
%P 654-658
Markdown (Informal)
[GRILLBot: A multi-modal conversational agent for complex real-world tasks](https://aclanthology.org/2022.sigdial-1.63) (Gemmell et al., SIGDIAL 2022)
ACL