@inproceedings{gangadharaiah-narayanaswamy-2020-recursive,
title = "Recursive Template-based Frame Generation for Task Oriented Dialog",
author = "Gangadharaiah, Rashmi and
Narayanaswamy, Balakrishnan",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.186",
doi = "10.18653/v1/2020.acl-main.186",
pages = "2059--2064",
abstract = "The Natural Language Understanding (NLU) component in task oriented dialog systems processes a user{'}s request and converts it into structured information that can be consumed by downstream components such as the Dialog State Tracker (DST). This information is typically represented as a semantic frame that captures the intent and slot-labels provided by the user. We first show that such a shallow representation is insufficient for complex dialog scenarios, because it does not capture the recursive nature inherent in many domains. We propose a recursive, hierarchical frame-based representation and show how to learn it from data. We formulate the frame generation task as a template-based tree decoding task, where the decoder recursively generates a template and then fills slot values into the template. We extend local tree-based loss functions with terms that provide global supervision and show how to optimize them end-to-end. We achieve a small improvement on the widely used ATIS dataset and a much larger improvement on a more complex dataset we describe here.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gangadharaiah-narayanaswamy-2020-recursive">
<titleInfo>
<title>Recursive Template-based Frame Generation for Task Oriented Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Gangadharaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balakrishnan</namePart>
<namePart type="family">Narayanaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Natural Language Understanding (NLU) component in task oriented dialog systems processes a user’s request and converts it into structured information that can be consumed by downstream components such as the Dialog State Tracker (DST). This information is typically represented as a semantic frame that captures the intent and slot-labels provided by the user. We first show that such a shallow representation is insufficient for complex dialog scenarios, because it does not capture the recursive nature inherent in many domains. We propose a recursive, hierarchical frame-based representation and show how to learn it from data. We formulate the frame generation task as a template-based tree decoding task, where the decoder recursively generates a template and then fills slot values into the template. We extend local tree-based loss functions with terms that provide global supervision and show how to optimize them end-to-end. We achieve a small improvement on the widely used ATIS dataset and a much larger improvement on a more complex dataset we describe here.</abstract>
<identifier type="citekey">gangadharaiah-narayanaswamy-2020-recursive</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.186</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.186</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>2059</start>
<end>2064</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recursive Template-based Frame Generation for Task Oriented Dialog
%A Gangadharaiah, Rashmi
%A Narayanaswamy, Balakrishnan
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F gangadharaiah-narayanaswamy-2020-recursive
%X The Natural Language Understanding (NLU) component in task oriented dialog systems processes a user’s request and converts it into structured information that can be consumed by downstream components such as the Dialog State Tracker (DST). This information is typically represented as a semantic frame that captures the intent and slot-labels provided by the user. We first show that such a shallow representation is insufficient for complex dialog scenarios, because it does not capture the recursive nature inherent in many domains. We propose a recursive, hierarchical frame-based representation and show how to learn it from data. We formulate the frame generation task as a template-based tree decoding task, where the decoder recursively generates a template and then fills slot values into the template. We extend local tree-based loss functions with terms that provide global supervision and show how to optimize them end-to-end. We achieve a small improvement on the widely used ATIS dataset and a much larger improvement on a more complex dataset we describe here.
%R 10.18653/v1/2020.acl-main.186
%U https://aclanthology.org/2020.acl-main.186
%U https://doi.org/10.18653/v1/2020.acl-main.186
%P 2059-2064
Markdown (Informal)
[Recursive Template-based Frame Generation for Task Oriented Dialog](https://aclanthology.org/2020.acl-main.186) (Gangadharaiah & Narayanaswamy, ACL 2020)
ACL