@inproceedings{pruthi-etal-2020-weakly,
title = "Weakly- and Semi-supervised Evidence Extraction",
author = "Pruthi, Danish and
Dhingra, Bhuwan and
Neubig, Graham and
Lipton, Zachary C.",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.353",
doi = "10.18653/v1/2020.findings-emnlp.353",
pages = "3965--3970",
abstract = "For many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness. However, in practice, evidence annotations may only be available for a minority of training examples (if available at all). In this paper, we propose new methods to combine few evidence annotations (strong semi-supervision) with abundant document-level labels (weak supervision) for the task of evidence extraction. Evaluating on two classification tasks that feature evidence annotations, we find that our methods outperform baselines adapted from the interpretability literature to our task. Our approach yields gains with as few as hundred evidence annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pruthi-etal-2020-weakly">
<titleInfo>
<title>Weakly- and Semi-supervised Evidence Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danish</namePart>
<namePart type="family">Pruthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhuwan</namePart>
<namePart type="family">Dhingra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Lipton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness. However, in practice, evidence annotations may only be available for a minority of training examples (if available at all). In this paper, we propose new methods to combine few evidence annotations (strong semi-supervision) with abundant document-level labels (weak supervision) for the task of evidence extraction. Evaluating on two classification tasks that feature evidence annotations, we find that our methods outperform baselines adapted from the interpretability literature to our task. Our approach yields gains with as few as hundred evidence annotations.</abstract>
<identifier type="citekey">pruthi-etal-2020-weakly</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.353</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.353</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3965</start>
<end>3970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weakly- and Semi-supervised Evidence Extraction
%A Pruthi, Danish
%A Dhingra, Bhuwan
%A Neubig, Graham
%A Lipton, Zachary C.
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F pruthi-etal-2020-weakly
%X For many prediction tasks, stakeholders desire not only predictions but also supporting evidence that a human can use to verify its correctness. However, in practice, evidence annotations may only be available for a minority of training examples (if available at all). In this paper, we propose new methods to combine few evidence annotations (strong semi-supervision) with abundant document-level labels (weak supervision) for the task of evidence extraction. Evaluating on two classification tasks that feature evidence annotations, we find that our methods outperform baselines adapted from the interpretability literature to our task. Our approach yields gains with as few as hundred evidence annotations.
%R 10.18653/v1/2020.findings-emnlp.353
%U https://aclanthology.org/2020.findings-emnlp.353
%U https://doi.org/10.18653/v1/2020.findings-emnlp.353
%P 3965-3970
Markdown (Informal)
[Weakly- and Semi-supervised Evidence Extraction](https://aclanthology.org/2020.findings-emnlp.353) (Pruthi et al., Findings 2020)
ACL
- Danish Pruthi, Bhuwan Dhingra, Graham Neubig, and Zachary C. Lipton. 2020. Weakly- and Semi-supervised Evidence Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3965–3970, Online. Association for Computational Linguistics.