@inproceedings{berger-etal-2018-visual,
title = "Visual Supervision in Bootstrapped Information Extraction",
author = "Berger, Matthew and
Nagesh, Ajay and
Levine, Joshua and
Surdeanu, Mihai and
Zhang, Helen",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1229",
doi = "10.18653/v1/D18-1229",
pages = "2043--2053",
abstract = "We challenge a common assumption in active learning, that a list-based interface populated by informative samples provides for efficient and effective data annotation. We show how a 2D scatterplot populated with diverse and representative samples can yield improved models given the same time budget. We consider this for bootstrapping-based information extraction, in particular named entity classification, where human and machine jointly label data. To enable effective data annotation in a scatterplot, we have developed an embedding-based bootstrapping model that learns the distributional similarity of entities through the patterns that match them in a large data corpus, while being discriminative with respect to human-labeled and machine-promoted entities. We conducted a user study to assess the effectiveness of these different interfaces, and analyze bootstrapping performance in terms of human labeling accuracy, label quantity, and labeling consensus across multiple users. Our results suggest that supervision acquired from the scatterplot interface, despite being noisier, yields improvements in classification performance compared with the list interface, due to a larger quantity of supervision acquired.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berger-etal-2018-visual">
<titleInfo>
<title>Visual Supervision in Bootstrapped Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Berger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajay</namePart>
<namePart type="family">Nagesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Levine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We challenge a common assumption in active learning, that a list-based interface populated by informative samples provides for efficient and effective data annotation. We show how a 2D scatterplot populated with diverse and representative samples can yield improved models given the same time budget. We consider this for bootstrapping-based information extraction, in particular named entity classification, where human and machine jointly label data. To enable effective data annotation in a scatterplot, we have developed an embedding-based bootstrapping model that learns the distributional similarity of entities through the patterns that match them in a large data corpus, while being discriminative with respect to human-labeled and machine-promoted entities. We conducted a user study to assess the effectiveness of these different interfaces, and analyze bootstrapping performance in terms of human labeling accuracy, label quantity, and labeling consensus across multiple users. Our results suggest that supervision acquired from the scatterplot interface, despite being noisier, yields improvements in classification performance compared with the list interface, due to a larger quantity of supervision acquired.</abstract>
<identifier type="citekey">berger-etal-2018-visual</identifier>
<identifier type="doi">10.18653/v1/D18-1229</identifier>
<location>
<url>https://aclanthology.org/D18-1229</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>2043</start>
<end>2053</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Supervision in Bootstrapped Information Extraction
%A Berger, Matthew
%A Nagesh, Ajay
%A Levine, Joshua
%A Surdeanu, Mihai
%A Zhang, Helen
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F berger-etal-2018-visual
%X We challenge a common assumption in active learning, that a list-based interface populated by informative samples provides for efficient and effective data annotation. We show how a 2D scatterplot populated with diverse and representative samples can yield improved models given the same time budget. We consider this for bootstrapping-based information extraction, in particular named entity classification, where human and machine jointly label data. To enable effective data annotation in a scatterplot, we have developed an embedding-based bootstrapping model that learns the distributional similarity of entities through the patterns that match them in a large data corpus, while being discriminative with respect to human-labeled and machine-promoted entities. We conducted a user study to assess the effectiveness of these different interfaces, and analyze bootstrapping performance in terms of human labeling accuracy, label quantity, and labeling consensus across multiple users. Our results suggest that supervision acquired from the scatterplot interface, despite being noisier, yields improvements in classification performance compared with the list interface, due to a larger quantity of supervision acquired.
%R 10.18653/v1/D18-1229
%U https://aclanthology.org/D18-1229
%U https://doi.org/10.18653/v1/D18-1229
%P 2043-2053
Markdown (Informal)
[Visual Supervision in Bootstrapped Information Extraction](https://aclanthology.org/D18-1229) (Berger et al., EMNLP 2018)
ACL
- Matthew Berger, Ajay Nagesh, Joshua Levine, Mihai Surdeanu, and Helen Zhang. 2018. Visual Supervision in Bootstrapped Information Extraction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2043–2053, Brussels, Belgium. Association for Computational Linguistics.