@inproceedings{chang-etal-2022-programmable,
title = "Programmable Annotation with Diversed Heuristics and Data Denoising",
author = "Chang, Ernie and
Marin, Alex and
Demberg, Vera",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.237",
pages = "2681--2691",
abstract = "Neural natural language generation (NLG) and understanding (NLU) models are costly and require massive amounts of annotated data to be competitive. Recent data programming frameworks address this bottleneck by allowing human supervision to be provided as a set of labeling functions to construct generative models that synthesize weak labels at scale. However, these labeling functions are difficult to build from scratch for NLG/NLU models, as they often require complex rule sets to be specified. To this end, we propose a novel data programming framework that can jointly construct labeled data for language generation and understanding tasks {--} by allowing the annotators to modify an automatically-inferred alignment rule set between sequence labels and text, instead of writing rules from scratch. Further, to mitigate the effect of poor quality labels, we propose a dually-regularized denoising mechanism for optimizing the NLU and NLG models. On two benchmarks we show that the framework can generate high-quality data that comes within a 1.48 BLEU and 6.42 slot F1 of the 100{\%} human-labeled data (42k instances) with just 100 labeled data samples {--} outperforming benchmark annotation frameworks and other semi-supervised approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2022-programmable">
<titleInfo>
<title>Programmable Annotation with Diversed Heuristics and Data Denoising</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernie</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Marin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural natural language generation (NLG) and understanding (NLU) models are costly and require massive amounts of annotated data to be competitive. Recent data programming frameworks address this bottleneck by allowing human supervision to be provided as a set of labeling functions to construct generative models that synthesize weak labels at scale. However, these labeling functions are difficult to build from scratch for NLG/NLU models, as they often require complex rule sets to be specified. To this end, we propose a novel data programming framework that can jointly construct labeled data for language generation and understanding tasks – by allowing the annotators to modify an automatically-inferred alignment rule set between sequence labels and text, instead of writing rules from scratch. Further, to mitigate the effect of poor quality labels, we propose a dually-regularized denoising mechanism for optimizing the NLU and NLG models. On two benchmarks we show that the framework can generate high-quality data that comes within a 1.48 BLEU and 6.42 slot F1 of the 100% human-labeled data (42k instances) with just 100 labeled data samples – outperforming benchmark annotation frameworks and other semi-supervised approaches.</abstract>
<identifier type="citekey">chang-etal-2022-programmable</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.237</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>2681</start>
<end>2691</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Programmable Annotation with Diversed Heuristics and Data Denoising
%A Chang, Ernie
%A Marin, Alex
%A Demberg, Vera
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F chang-etal-2022-programmable
%X Neural natural language generation (NLG) and understanding (NLU) models are costly and require massive amounts of annotated data to be competitive. Recent data programming frameworks address this bottleneck by allowing human supervision to be provided as a set of labeling functions to construct generative models that synthesize weak labels at scale. However, these labeling functions are difficult to build from scratch for NLG/NLU models, as they often require complex rule sets to be specified. To this end, we propose a novel data programming framework that can jointly construct labeled data for language generation and understanding tasks – by allowing the annotators to modify an automatically-inferred alignment rule set between sequence labels and text, instead of writing rules from scratch. Further, to mitigate the effect of poor quality labels, we propose a dually-regularized denoising mechanism for optimizing the NLU and NLG models. On two benchmarks we show that the framework can generate high-quality data that comes within a 1.48 BLEU and 6.42 slot F1 of the 100% human-labeled data (42k instances) with just 100 labeled data samples – outperforming benchmark annotation frameworks and other semi-supervised approaches.
%U https://aclanthology.org/2022.coling-1.237
%P 2681-2691
Markdown (Informal)
[Programmable Annotation with Diversed Heuristics and Data Denoising](https://aclanthology.org/2022.coling-1.237) (Chang et al., COLING 2022)
ACL