@inproceedings{burnyshev-etal-2021-single,
title = "Single Example Can Improve Zero-Shot Data Generation",
author = "Burnyshev, Pavel and
Malykh, Valentin and
Bout, Andrey and
Artemova, Ekaterina and
Piontkovskaya, Irina",
editor = "Belz, Anya and
Fan, Angela and
Reiter, Ehud and
Sripada, Yaji",
booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",
month = aug,
year = "2021",
address = "Aberdeen, Scotland, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.inlg-1.20/",
doi = "10.18653/v1/2021.inlg-1.20",
pages = "201--211",
abstract = "Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such datasets is time- and labor-consuming, we propose to use text generation methods to gather datasets. The generator should be trained to generate utterances that belong to the given intent. We explore two approaches to the generation of task-oriented utterances: in the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training. In the one-shot approach, the model is presented with a single utterance from a test intent. We perform a thorough automatic, and human evaluation of the intrinsic properties of two-generation approaches. The attributes of the generated data are close to original test sets, collected via crowd-sourcing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burnyshev-etal-2021-single">
<titleInfo>
<title>Single Example Can Improve Zero-Shot Data Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Burnyshev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Bout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Piontkovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</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">Aberdeen, Scotland, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such datasets is time- and labor-consuming, we propose to use text generation methods to gather datasets. The generator should be trained to generate utterances that belong to the given intent. We explore two approaches to the generation of task-oriented utterances: in the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training. In the one-shot approach, the model is presented with a single utterance from a test intent. We perform a thorough automatic, and human evaluation of the intrinsic properties of two-generation approaches. The attributes of the generated data are close to original test sets, collected via crowd-sourcing.</abstract>
<identifier type="citekey">burnyshev-etal-2021-single</identifier>
<identifier type="doi">10.18653/v1/2021.inlg-1.20</identifier>
<location>
<url>https://aclanthology.org/2021.inlg-1.20/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>201</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Single Example Can Improve Zero-Shot Data Generation
%A Burnyshev, Pavel
%A Malykh, Valentin
%A Bout, Andrey
%A Artemova, Ekaterina
%A Piontkovskaya, Irina
%Y Belz, Anya
%Y Fan, Angela
%Y Reiter, Ehud
%Y Sripada, Yaji
%S Proceedings of the 14th International Conference on Natural Language Generation
%D 2021
%8 August
%I Association for Computational Linguistics
%C Aberdeen, Scotland, UK
%F burnyshev-etal-2021-single
%X Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such datasets is time- and labor-consuming, we propose to use text generation methods to gather datasets. The generator should be trained to generate utterances that belong to the given intent. We explore two approaches to the generation of task-oriented utterances: in the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training. In the one-shot approach, the model is presented with a single utterance from a test intent. We perform a thorough automatic, and human evaluation of the intrinsic properties of two-generation approaches. The attributes of the generated data are close to original test sets, collected via crowd-sourcing.
%R 10.18653/v1/2021.inlg-1.20
%U https://aclanthology.org/2021.inlg-1.20/
%U https://doi.org/10.18653/v1/2021.inlg-1.20
%P 201-211
Markdown (Informal)
[Single Example Can Improve Zero-Shot Data Generation](https://aclanthology.org/2021.inlg-1.20/) (Burnyshev et al., INLG 2021)
ACL
- Pavel Burnyshev, Valentin Malykh, Andrey Bout, Ekaterina Artemova, and Irina Piontkovskaya. 2021. Single Example Can Improve Zero-Shot Data Generation. In Proceedings of the 14th International Conference on Natural Language Generation, pages 201–211, Aberdeen, Scotland, UK. Association for Computational Linguistics.