@inproceedings{zhang-etal-2024-scier,
title = "{S}ci{ER}: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents",
author = "Zhang, Qi and
Chen, Zhijia and
Pan, Huitong and
Caragea, Cornelia and
Latecki, Longin and
Dragut, Eduard",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.726",
pages = "13083--13100",
abstract = "Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data (entities and relations). Several datasets have been proposed for training and validating SciIE models. However, due to the high complexity and cost of annotating scientific texts, those datasets restrict their annotations to specific parts of paper, such as abstracts, resulting in the loss of diverse entity mentions and relations in context. In this paper, we release a new entity and relation extraction dataset for entities related to datasets, methods, and tasks in scientific articles. Our dataset contains 106 manually annotated full-text scientific publications with over 24k entities and 12k relations. To capture the intricate use and interactions among entities in full texts, our dataset contains a fine-grained tag set for relations. Additionally, we provide an out-of-distribution test set to offer a more realistic evaluation. We conduct comprehensive experiments, including state-of-the-art supervised models and our proposed LLM-based baselines, and highlight the challenges presented by our dataset, encouraging the development of innovative models to further the field of SciIE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-scier">
<titleInfo>
<title>SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijia</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huitong</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longin</namePart>
<namePart type="family">Latecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Dragut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data (entities and relations). Several datasets have been proposed for training and validating SciIE models. However, due to the high complexity and cost of annotating scientific texts, those datasets restrict their annotations to specific parts of paper, such as abstracts, resulting in the loss of diverse entity mentions and relations in context. In this paper, we release a new entity and relation extraction dataset for entities related to datasets, methods, and tasks in scientific articles. Our dataset contains 106 manually annotated full-text scientific publications with over 24k entities and 12k relations. To capture the intricate use and interactions among entities in full texts, our dataset contains a fine-grained tag set for relations. Additionally, we provide an out-of-distribution test set to offer a more realistic evaluation. We conduct comprehensive experiments, including state-of-the-art supervised models and our proposed LLM-based baselines, and highlight the challenges presented by our dataset, encouraging the development of innovative models to further the field of SciIE.</abstract>
<identifier type="citekey">zhang-etal-2024-scier</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.726</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>13083</start>
<end>13100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents
%A Zhang, Qi
%A Chen, Zhijia
%A Pan, Huitong
%A Caragea, Cornelia
%A Latecki, Longin
%A Dragut, Eduard
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhang-etal-2024-scier
%X Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data (entities and relations). Several datasets have been proposed for training and validating SciIE models. However, due to the high complexity and cost of annotating scientific texts, those datasets restrict their annotations to specific parts of paper, such as abstracts, resulting in the loss of diverse entity mentions and relations in context. In this paper, we release a new entity and relation extraction dataset for entities related to datasets, methods, and tasks in scientific articles. Our dataset contains 106 manually annotated full-text scientific publications with over 24k entities and 12k relations. To capture the intricate use and interactions among entities in full texts, our dataset contains a fine-grained tag set for relations. Additionally, we provide an out-of-distribution test set to offer a more realistic evaluation. We conduct comprehensive experiments, including state-of-the-art supervised models and our proposed LLM-based baselines, and highlight the challenges presented by our dataset, encouraging the development of innovative models to further the field of SciIE.
%U https://aclanthology.org/2024.emnlp-main.726
%P 13083-13100
Markdown (Informal)
[SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents](https://aclanthology.org/2024.emnlp-main.726) (Zhang et al., EMNLP 2024)
ACL
- Qi Zhang, Zhijia Chen, Huitong Pan, Cornelia Caragea, Longin Latecki, and Eduard Dragut. 2024. SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13083–13100, Miami, Florida, USA. Association for Computational Linguistics.