@inproceedings{tiktinsky-etal-2022-dataset,
title = "A Dataset for N-ary Relation Extraction of Drug Combinations",
author = "Tiktinsky, Aryeh and
Viswanathan, Vijay and
Niezni, Danna and
Meron Azagury, Dana and
Shamay, Yosi and
Taub-Tabib, Hillel and
Hope, Tom and
Goldberg, Yoav",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.233/",
doi = "10.18653/v1/2022.naacl-main.233",
pages = "3190--3203",
abstract = "Combination therapies have become the standard of care for diseases such as cancer, tuberculosis, malaria and HIV. However, the combinatorial set of available multi-drug treatments creates a challenge in identifying effective combination therapies available in a situation. To assist medical professionals in identifying beneficial drug-combinations, we construct an expert-annotated dataset for extracting information about the efficacy of drug combinations from the scientific literature. Beyond its practical utility, the dataset also presents a unique NLP challenge, as the first relation extraction dataset consisting of variable-length relations. Furthermore, the relations in this dataset predominantly require language understanding beyond the sentence level, adding to the challenge of this task. We provide a promising baseline model and identify clear areas for further improvement. We release our dataset (\url{https://huggingface.co/datasets/allenai/drug-combo-extraction}), code (\url{https://github.com/allenai/drug-combo-extraction}) and baseline models (\url{https://huggingface.co/allenai/drug-combo-classifier-pubmedbert-dapt}) publicly to encourage the NLP community to participate in this task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tiktinsky-etal-2022-dataset">
<titleInfo>
<title>A Dataset for N-ary Relation Extraction of Drug Combinations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aryeh</namePart>
<namePart type="family">Tiktinsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="family">Viswanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danna</namePart>
<namePart type="family">Niezni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Meron Azagury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yosi</namePart>
<namePart type="family">Shamay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hillel</namePart>
<namePart type="family">Taub-Tabib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Combination therapies have become the standard of care for diseases such as cancer, tuberculosis, malaria and HIV. However, the combinatorial set of available multi-drug treatments creates a challenge in identifying effective combination therapies available in a situation. To assist medical professionals in identifying beneficial drug-combinations, we construct an expert-annotated dataset for extracting information about the efficacy of drug combinations from the scientific literature. Beyond its practical utility, the dataset also presents a unique NLP challenge, as the first relation extraction dataset consisting of variable-length relations. Furthermore, the relations in this dataset predominantly require language understanding beyond the sentence level, adding to the challenge of this task. We provide a promising baseline model and identify clear areas for further improvement. We release our dataset (https://huggingface.co/datasets/allenai/drug-combo-extraction), code (https://github.com/allenai/drug-combo-extraction) and baseline models (https://huggingface.co/allenai/drug-combo-classifier-pubmedbert-dapt) publicly to encourage the NLP community to participate in this task.</abstract>
<identifier type="citekey">tiktinsky-etal-2022-dataset</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.233</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.233/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3190</start>
<end>3203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset for N-ary Relation Extraction of Drug Combinations
%A Tiktinsky, Aryeh
%A Viswanathan, Vijay
%A Niezni, Danna
%A Meron Azagury, Dana
%A Shamay, Yosi
%A Taub-Tabib, Hillel
%A Hope, Tom
%A Goldberg, Yoav
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F tiktinsky-etal-2022-dataset
%X Combination therapies have become the standard of care for diseases such as cancer, tuberculosis, malaria and HIV. However, the combinatorial set of available multi-drug treatments creates a challenge in identifying effective combination therapies available in a situation. To assist medical professionals in identifying beneficial drug-combinations, we construct an expert-annotated dataset for extracting information about the efficacy of drug combinations from the scientific literature. Beyond its practical utility, the dataset also presents a unique NLP challenge, as the first relation extraction dataset consisting of variable-length relations. Furthermore, the relations in this dataset predominantly require language understanding beyond the sentence level, adding to the challenge of this task. We provide a promising baseline model and identify clear areas for further improvement. We release our dataset (https://huggingface.co/datasets/allenai/drug-combo-extraction), code (https://github.com/allenai/drug-combo-extraction) and baseline models (https://huggingface.co/allenai/drug-combo-classifier-pubmedbert-dapt) publicly to encourage the NLP community to participate in this task.
%R 10.18653/v1/2022.naacl-main.233
%U https://aclanthology.org/2022.naacl-main.233/
%U https://doi.org/10.18653/v1/2022.naacl-main.233
%P 3190-3203
Markdown (Informal)
[A Dataset for N-ary Relation Extraction of Drug Combinations](https://aclanthology.org/2022.naacl-main.233/) (Tiktinsky et al., NAACL 2022)
ACL
- Aryeh Tiktinsky, Vijay Viswanathan, Danna Niezni, Dana Meron Azagury, Yosi Shamay, Hillel Taub-Tabib, Tom Hope, and Yoav Goldberg. 2022. A Dataset for N-ary Relation Extraction of Drug Combinations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3190–3203, Seattle, United States. Association for Computational Linguistics.