@inproceedings{thorne-klinger-2017-towards,
title = "Towards Confidence Estimation for Typed Protein-Protein Relation Extraction",
author = "Thorne, Camilo and
Klinger, Roman",
editor = "Boytcheva, Svetla and
Cohen, Kevin Bretonnel and
Savova, Guergana and
Angelova, Galia",
booktitle = "Proceedings of the Biomedical {NLP} Workshop associated with {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-044-1_008",
doi = "10.26615/978-954-452-044-1_008",
pages = "55--63",
abstract = "Systems which build on top of information extraction are typically challenged to extract knowledge that, while correct, is not yet well-known. We hypothesize that a good confidence measure for relational information has the property that such interesting information is found between information extracted with very high confidence and very low confidence. We discuss confidence estimation for the domain of biomedical protein-protein relation discovery in biomedical literature. As facts reported in papers take some time to be validated and recorded in biomedical databases, such task gives rise to large quantities of unknown but potentially true candidate relations. It is thus important to rank them based on supporting evidence rather than discard them. In this paper, we discuss this task and propose different approaches for confidence estimation and a pipeline to evaluate such methods. We show that the most straight-forward approach, a combination of different confidence measures from pipeline modules seems not to work well. We discuss this negative result and pinpoint potential future research directions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thorne-klinger-2017-towards">
<titleInfo>
<title>Towards Confidence Estimation for Typed Protein-Protein Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Camilo</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Biomedical NLP Workshop associated with RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Boytcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guergana</namePart>
<namePart type="family">Savova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Systems which build on top of information extraction are typically challenged to extract knowledge that, while correct, is not yet well-known. We hypothesize that a good confidence measure for relational information has the property that such interesting information is found between information extracted with very high confidence and very low confidence. We discuss confidence estimation for the domain of biomedical protein-protein relation discovery in biomedical literature. As facts reported in papers take some time to be validated and recorded in biomedical databases, such task gives rise to large quantities of unknown but potentially true candidate relations. It is thus important to rank them based on supporting evidence rather than discard them. In this paper, we discuss this task and propose different approaches for confidence estimation and a pipeline to evaluate such methods. We show that the most straight-forward approach, a combination of different confidence measures from pipeline modules seems not to work well. We discuss this negative result and pinpoint potential future research directions.</abstract>
<identifier type="citekey">thorne-klinger-2017-towards</identifier>
<identifier type="doi">10.26615/978-954-452-044-1_008</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>55</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Confidence Estimation for Typed Protein-Protein Relation Extraction
%A Thorne, Camilo
%A Klinger, Roman
%Y Boytcheva, Svetla
%Y Cohen, Kevin Bretonnel
%Y Savova, Guergana
%Y Angelova, Galia
%S Proceedings of the Biomedical NLP Workshop associated with RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F thorne-klinger-2017-towards
%X Systems which build on top of information extraction are typically challenged to extract knowledge that, while correct, is not yet well-known. We hypothesize that a good confidence measure for relational information has the property that such interesting information is found between information extracted with very high confidence and very low confidence. We discuss confidence estimation for the domain of biomedical protein-protein relation discovery in biomedical literature. As facts reported in papers take some time to be validated and recorded in biomedical databases, such task gives rise to large quantities of unknown but potentially true candidate relations. It is thus important to rank them based on supporting evidence rather than discard them. In this paper, we discuss this task and propose different approaches for confidence estimation and a pipeline to evaluate such methods. We show that the most straight-forward approach, a combination of different confidence measures from pipeline modules seems not to work well. We discuss this negative result and pinpoint potential future research directions.
%R 10.26615/978-954-452-044-1_008
%U https://doi.org/10.26615/978-954-452-044-1_008
%P 55-63
Markdown (Informal)
[Towards Confidence Estimation for Typed Protein-Protein Relation Extraction](https://doi.org/10.26615/978-954-452-044-1_008) (Thorne & Klinger, RANLP 2017)
ACL