@inproceedings{swarup-etal-2020-instance,
title = "{A}n {I}nstance {L}evel {A}pproach for {S}hallow {S}emantic {P}arsing in {S}cientific {P}rocedural {T}ext",
author = "Swarup, Daivik and
Bajaj, Ahsaas and
Mysore, Sheshera and
O{'}Gorman, Tim and
Das, Rajarshi and
McCallum, Andrew",
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.270/",
doi = "10.18653/v1/2020.findings-emnlp.270",
pages = "3010--3017",
abstract = "In specific domains, such as procedural scientific text, human labeled data for shallow semantic parsing is especially limited and expensive to create. Fortunately, such specific domains often use rather formulaic writing, such that the different ways of expressing relations in a small number of grammatically similar labeled sentences may provide high coverage of semantic structures in the corpus, through an appropriately rich similarity metric. In light of this opportunity, this paper explores an instance-based approach to the relation prediction sub-task within shallow semantic parsing, in which semantic labels from structurally similar sentences in the training set are copied to test sentences. Candidate similar sentences are retrieved using SciBERT embeddings. For labels where it is possible to copy from a similar sentence we employ an instance level copy network, when this is not possible, a globally shared parametric model is employed. Experiments show our approach outperforms both baseline and prior methods by 0.75 to 3 F1 absolute in the Wet Lab Protocol Corpus and 1 F1 absolute in the Materials Science Procedural Text Corpus."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="swarup-etal-2020-instance">
<titleInfo>
<title>An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daivik</namePart>
<namePart type="family">Swarup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahsaas</namePart>
<namePart type="family">Bajaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheshera</namePart>
<namePart type="family">Mysore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">O’Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajarshi</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</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>In specific domains, such as procedural scientific text, human labeled data for shallow semantic parsing is especially limited and expensive to create. Fortunately, such specific domains often use rather formulaic writing, such that the different ways of expressing relations in a small number of grammatically similar labeled sentences may provide high coverage of semantic structures in the corpus, through an appropriately rich similarity metric. In light of this opportunity, this paper explores an instance-based approach to the relation prediction sub-task within shallow semantic parsing, in which semantic labels from structurally similar sentences in the training set are copied to test sentences. Candidate similar sentences are retrieved using SciBERT embeddings. For labels where it is possible to copy from a similar sentence we employ an instance level copy network, when this is not possible, a globally shared parametric model is employed. Experiments show our approach outperforms both baseline and prior methods by 0.75 to 3 F1 absolute in the Wet Lab Protocol Corpus and 1 F1 absolute in the Materials Science Procedural Text Corpus.</abstract>
<identifier type="citekey">swarup-etal-2020-instance</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.270</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.270/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3010</start>
<end>3017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text
%A Swarup, Daivik
%A Bajaj, Ahsaas
%A Mysore, Sheshera
%A O’Gorman, Tim
%A Das, Rajarshi
%A McCallum, Andrew
%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 swarup-etal-2020-instance
%X In specific domains, such as procedural scientific text, human labeled data for shallow semantic parsing is especially limited and expensive to create. Fortunately, such specific domains often use rather formulaic writing, such that the different ways of expressing relations in a small number of grammatically similar labeled sentences may provide high coverage of semantic structures in the corpus, through an appropriately rich similarity metric. In light of this opportunity, this paper explores an instance-based approach to the relation prediction sub-task within shallow semantic parsing, in which semantic labels from structurally similar sentences in the training set are copied to test sentences. Candidate similar sentences are retrieved using SciBERT embeddings. For labels where it is possible to copy from a similar sentence we employ an instance level copy network, when this is not possible, a globally shared parametric model is employed. Experiments show our approach outperforms both baseline and prior methods by 0.75 to 3 F1 absolute in the Wet Lab Protocol Corpus and 1 F1 absolute in the Materials Science Procedural Text Corpus.
%R 10.18653/v1/2020.findings-emnlp.270
%U https://aclanthology.org/2020.findings-emnlp.270/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.270
%P 3010-3017
Markdown (Informal)
[An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text](https://aclanthology.org/2020.findings-emnlp.270/) (Swarup et al., Findings 2020)
ACL