@inproceedings{qin-etal-2021-relation,
title = "Relation Extraction with Word Graphs from N-grams",
author = "Qin, Han and
Tian, Yuanhe and
Song, Yan",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.228",
doi = "10.18653/v1/2021.emnlp-main.228",
pages = "2860--2868",
abstract = "Most recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to incorporate syntax-driven contextual information to improve model performance, with little attention paid to the limitation where high-quality dependency parsers in most cases unavailable, especially for in-domain scenarios. To address this limitation, in this paper, we propose attentive graph convolutional networks (A-GCN) to improve neural RE methods with an unsupervised manner to build the context graph, without relying on the existence of a dependency parser. Specifically, we construct the graph from n-grams extracted from a lexicon built from pointwise mutual information (PMI) and apply attention over the graph. Therefore, different word pairs from the contexts within and across n-grams are weighted in the model and facilitate RE accordingly. Experimental results with further analyses on two English benchmark datasets for RE demonstrate the effectiveness of our approach, where state-of-the-art performance is observed on both datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2021-relation">
<titleInfo>
<title>Relation Extraction with Word Graphs from N-grams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanhe</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to incorporate syntax-driven contextual information to improve model performance, with little attention paid to the limitation where high-quality dependency parsers in most cases unavailable, especially for in-domain scenarios. To address this limitation, in this paper, we propose attentive graph convolutional networks (A-GCN) to improve neural RE methods with an unsupervised manner to build the context graph, without relying on the existence of a dependency parser. Specifically, we construct the graph from n-grams extracted from a lexicon built from pointwise mutual information (PMI) and apply attention over the graph. Therefore, different word pairs from the contexts within and across n-grams are weighted in the model and facilitate RE accordingly. Experimental results with further analyses on two English benchmark datasets for RE demonstrate the effectiveness of our approach, where state-of-the-art performance is observed on both datasets.</abstract>
<identifier type="citekey">qin-etal-2021-relation</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.228</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.228</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2860</start>
<end>2868</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Relation Extraction with Word Graphs from N-grams
%A Qin, Han
%A Tian, Yuanhe
%A Song, Yan
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F qin-etal-2021-relation
%X Most recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to incorporate syntax-driven contextual information to improve model performance, with little attention paid to the limitation where high-quality dependency parsers in most cases unavailable, especially for in-domain scenarios. To address this limitation, in this paper, we propose attentive graph convolutional networks (A-GCN) to improve neural RE methods with an unsupervised manner to build the context graph, without relying on the existence of a dependency parser. Specifically, we construct the graph from n-grams extracted from a lexicon built from pointwise mutual information (PMI) and apply attention over the graph. Therefore, different word pairs from the contexts within and across n-grams are weighted in the model and facilitate RE accordingly. Experimental results with further analyses on two English benchmark datasets for RE demonstrate the effectiveness of our approach, where state-of-the-art performance is observed on both datasets.
%R 10.18653/v1/2021.emnlp-main.228
%U https://aclanthology.org/2021.emnlp-main.228
%U https://doi.org/10.18653/v1/2021.emnlp-main.228
%P 2860-2868
Markdown (Informal)
[Relation Extraction with Word Graphs from N-grams](https://aclanthology.org/2021.emnlp-main.228) (Qin et al., EMNLP 2021)
ACL
- Han Qin, Yuanhe Tian, and Yan Song. 2021. Relation Extraction with Word Graphs from N-grams. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2860–2868, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.