@inproceedings{jolly-etal-2020-data,
title = "Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems",
author = "Jolly, Shailza and
Falke, Tobias and
Tirkaz, Caglar and
Sorokin, Daniil",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.2",
doi = "10.18653/v1/2020.coling-industry.2",
pages = "10--20",
abstract = "Recent progress through advanced neural models pushed the performance of task-oriented dialog systems to almost perfect accuracy on existing benchmark datasets for intent classification and slot labeling. However, in evolving real-world dialog systems, where new functionality is regularly added, a major additional challenge is the lack of annotated training data for such new functionality, as the necessary data collection efforts are laborious and time-consuming. A potential solution to reduce the effort is to augment initial seed data by paraphrasing existing utterances automatically. In this paper, we propose a new, data-efficient approach following this idea. Using an interpretation-to-text model for paraphrase generation, we are able to rely on existing dialog system training data, and, in combination with shuffling-based sampling techniques, we can obtain diverse and novel paraphrases from small amounts of seed data. In experiments on a public dataset and with a real-world dialog system, we observe improvements for both intent classification and slot labeling, demonstrating the usefulness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jolly-etal-2020-data">
<titleInfo>
<title>Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shailza</namePart>
<namePart type="family">Jolly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Falke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caglar</namePart>
<namePart type="family">Tirkaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Sorokin</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 28th International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent progress through advanced neural models pushed the performance of task-oriented dialog systems to almost perfect accuracy on existing benchmark datasets for intent classification and slot labeling. However, in evolving real-world dialog systems, where new functionality is regularly added, a major additional challenge is the lack of annotated training data for such new functionality, as the necessary data collection efforts are laborious and time-consuming. A potential solution to reduce the effort is to augment initial seed data by paraphrasing existing utterances automatically. In this paper, we propose a new, data-efficient approach following this idea. Using an interpretation-to-text model for paraphrase generation, we are able to rely on existing dialog system training data, and, in combination with shuffling-based sampling techniques, we can obtain diverse and novel paraphrases from small amounts of seed data. In experiments on a public dataset and with a real-world dialog system, we observe improvements for both intent classification and slot labeling, demonstrating the usefulness of our approach.</abstract>
<identifier type="citekey">jolly-etal-2020-data</identifier>
<identifier type="doi">10.18653/v1/2020.coling-industry.2</identifier>
<location>
<url>https://aclanthology.org/2020.coling-industry.2</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>10</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems
%A Jolly, Shailza
%A Falke, Tobias
%A Tirkaz, Caglar
%A Sorokin, Daniil
%Y Clifton, Ann
%Y Napoles, Courtney
%S Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F jolly-etal-2020-data
%X Recent progress through advanced neural models pushed the performance of task-oriented dialog systems to almost perfect accuracy on existing benchmark datasets for intent classification and slot labeling. However, in evolving real-world dialog systems, where new functionality is regularly added, a major additional challenge is the lack of annotated training data for such new functionality, as the necessary data collection efforts are laborious and time-consuming. A potential solution to reduce the effort is to augment initial seed data by paraphrasing existing utterances automatically. In this paper, we propose a new, data-efficient approach following this idea. Using an interpretation-to-text model for paraphrase generation, we are able to rely on existing dialog system training data, and, in combination with shuffling-based sampling techniques, we can obtain diverse and novel paraphrases from small amounts of seed data. In experiments on a public dataset and with a real-world dialog system, we observe improvements for both intent classification and slot labeling, demonstrating the usefulness of our approach.
%R 10.18653/v1/2020.coling-industry.2
%U https://aclanthology.org/2020.coling-industry.2
%U https://doi.org/10.18653/v1/2020.coling-industry.2
%P 10-20
Markdown (Informal)
[Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems](https://aclanthology.org/2020.coling-industry.2) (Jolly et al., COLING 2020)
ACL