@inproceedings{du-etal-2020-schema,
title = "Schema-Guided Natural Language Generation",
author = "Du, Yuheng and
Oraby, Shereen and
Perera, Vittorio and
Shen, Minmin and
Narayan-Chen, Anjali and
Chung, Tagyoung and
Venkatesh, Anushree and
Hakkani-Tur, Dilek",
editor = "Davis, Brian and
Graham, Yvette and
Kelleher, John and
Sripada, Yaji",
booktitle = "Proceedings of the 13th International Conference on Natural Language Generation",
month = dec,
year = "2020",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.inlg-1.35",
doi = "10.18653/v1/2020.inlg-1.35",
pages = "283--295",
abstract = "Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To facilitate the training of neural network models, researchers created large datasets of paired utterances and their meaning representations. However, the creation of such datasets is an arduous task and they mostly consist of simple meaning representations composed of slot and value tokens to be realized. These representations do not include any contextual information that an NLG system can use when trying to generalize, such as domain information and descriptions of slots and values. In this paper, we present the novel task of Schema-Guided Natural Language Generation (SG-NLG). Here, the goal is still to generate a natural language prompt, but in SG-NLG, the input MRs are paired with rich schemata providing contextual information. To generate a dataset for SG-NLG we re-purpose an existing dataset for another task: dialog state tracking, which includes a large and rich schema spanning multiple different attributes, including information about the domain, user intent, and slot descriptions. We train different state-of-the-art models for neural natural language generation on this dataset and show that in many cases, including rich schema information allows our models to produce higher quality outputs both in terms of semantics and diversity. We also conduct experiments comparing model performance on seen versus unseen domains, and present a human evaluation demonstrating high ratings for overall output quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2020-schema">
<titleInfo>
<title>Schema-Guided Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuheng</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shereen</namePart>
<namePart type="family">Oraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vittorio</namePart>
<namePart type="family">Perera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minmin</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjali</namePart>
<namePart type="family">Narayan-Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tagyoung</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anushree</namePart>
<namePart type="family">Venkatesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Kelleher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaji</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To facilitate the training of neural network models, researchers created large datasets of paired utterances and their meaning representations. However, the creation of such datasets is an arduous task and they mostly consist of simple meaning representations composed of slot and value tokens to be realized. These representations do not include any contextual information that an NLG system can use when trying to generalize, such as domain information and descriptions of slots and values. In this paper, we present the novel task of Schema-Guided Natural Language Generation (SG-NLG). Here, the goal is still to generate a natural language prompt, but in SG-NLG, the input MRs are paired with rich schemata providing contextual information. To generate a dataset for SG-NLG we re-purpose an existing dataset for another task: dialog state tracking, which includes a large and rich schema spanning multiple different attributes, including information about the domain, user intent, and slot descriptions. We train different state-of-the-art models for neural natural language generation on this dataset and show that in many cases, including rich schema information allows our models to produce higher quality outputs both in terms of semantics and diversity. We also conduct experiments comparing model performance on seen versus unseen domains, and present a human evaluation demonstrating high ratings for overall output quality.</abstract>
<identifier type="citekey">du-etal-2020-schema</identifier>
<identifier type="doi">10.18653/v1/2020.inlg-1.35</identifier>
<location>
<url>https://aclanthology.org/2020.inlg-1.35</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>283</start>
<end>295</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Schema-Guided Natural Language Generation
%A Du, Yuheng
%A Oraby, Shereen
%A Perera, Vittorio
%A Shen, Minmin
%A Narayan-Chen, Anjali
%A Chung, Tagyoung
%A Venkatesh, Anushree
%A Hakkani-Tur, Dilek
%Y Davis, Brian
%Y Graham, Yvette
%Y Kelleher, John
%Y Sripada, Yaji
%S Proceedings of the 13th International Conference on Natural Language Generation
%D 2020
%8 December
%I Association for Computational Linguistics
%C Dublin, Ireland
%F du-etal-2020-schema
%X Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To facilitate the training of neural network models, researchers created large datasets of paired utterances and their meaning representations. However, the creation of such datasets is an arduous task and they mostly consist of simple meaning representations composed of slot and value tokens to be realized. These representations do not include any contextual information that an NLG system can use when trying to generalize, such as domain information and descriptions of slots and values. In this paper, we present the novel task of Schema-Guided Natural Language Generation (SG-NLG). Here, the goal is still to generate a natural language prompt, but in SG-NLG, the input MRs are paired with rich schemata providing contextual information. To generate a dataset for SG-NLG we re-purpose an existing dataset for another task: dialog state tracking, which includes a large and rich schema spanning multiple different attributes, including information about the domain, user intent, and slot descriptions. We train different state-of-the-art models for neural natural language generation on this dataset and show that in many cases, including rich schema information allows our models to produce higher quality outputs both in terms of semantics and diversity. We also conduct experiments comparing model performance on seen versus unseen domains, and present a human evaluation demonstrating high ratings for overall output quality.
%R 10.18653/v1/2020.inlg-1.35
%U https://aclanthology.org/2020.inlg-1.35
%U https://doi.org/10.18653/v1/2020.inlg-1.35
%P 283-295
Markdown (Informal)
[Schema-Guided Natural Language Generation](https://aclanthology.org/2020.inlg-1.35) (Du et al., INLG 2020)
ACL
- Yuheng Du, Shereen Oraby, Vittorio Perera, Minmin Shen, Anjali Narayan-Chen, Tagyoung Chung, Anushree Venkatesh, and Dilek Hakkani-Tur. 2020. Schema-Guided Natural Language Generation. In Proceedings of the 13th International Conference on Natural Language Generation, pages 283–295, Dublin, Ireland. Association for Computational Linguistics.