@inproceedings{mallart-etal-2021-active,
title = "Active Learning for Interactive Relation Extraction in a {F}rench Newspaper{'}s Articles",
author = "Mallart, Cyrielle and
Le Nouy, Michel and
Gravier, Guillaume and
S{\'e}billot, Pascale",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.101",
pages = "886--894",
abstract = "Relation extraction is a subtask of natural langage processing that has seen many improvements in recent years, with the advent of complex pre-trained architectures. Many of these state-of-the-art approaches are tested against benchmarks with labelled sentences containing tagged entities, and require important pre-training and fine-tuning on task-specific data. However, in a real use-case scenario such as in a newspaper company mostly dedicated to local information, relations are of varied, highly specific type, with virtually no annotated data for such relations, and many entities co-occur in a sentence without being related. We question the use of supervised state-of-the-art models in such a context, where resources such as time, computing power and human annotators are limited. To adapt to these constraints, we experiment with an active-learning based relation extraction pipeline, consisting of a binary LSTM-based lightweight model for detecting the relations that do exist, and a state-of-the-art model for relation classification. We compare several choices for classification models in this scenario, from basic word embedding averaging, to graph neural networks and Bert-based ones, as well as several active learning acquisition strategies, in order to find the most cost-efficient yet accurate approach in our French largest daily newspaper company{'}s use case.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mallart-etal-2021-active">
<titleInfo>
<title>Active Learning for Interactive Relation Extraction in a French Newspaper’s Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cyrielle</namePart>
<namePart type="family">Mallart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Le Nouy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gravier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Sébillot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</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">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Relation extraction is a subtask of natural langage processing that has seen many improvements in recent years, with the advent of complex pre-trained architectures. Many of these state-of-the-art approaches are tested against benchmarks with labelled sentences containing tagged entities, and require important pre-training and fine-tuning on task-specific data. However, in a real use-case scenario such as in a newspaper company mostly dedicated to local information, relations are of varied, highly specific type, with virtually no annotated data for such relations, and many entities co-occur in a sentence without being related. We question the use of supervised state-of-the-art models in such a context, where resources such as time, computing power and human annotators are limited. To adapt to these constraints, we experiment with an active-learning based relation extraction pipeline, consisting of a binary LSTM-based lightweight model for detecting the relations that do exist, and a state-of-the-art model for relation classification. We compare several choices for classification models in this scenario, from basic word embedding averaging, to graph neural networks and Bert-based ones, as well as several active learning acquisition strategies, in order to find the most cost-efficient yet accurate approach in our French largest daily newspaper company’s use case.</abstract>
<identifier type="citekey">mallart-etal-2021-active</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.101</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>886</start>
<end>894</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Active Learning for Interactive Relation Extraction in a French Newspaper’s Articles
%A Mallart, Cyrielle
%A Le Nouy, Michel
%A Gravier, Guillaume
%A Sébillot, Pascale
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F mallart-etal-2021-active
%X Relation extraction is a subtask of natural langage processing that has seen many improvements in recent years, with the advent of complex pre-trained architectures. Many of these state-of-the-art approaches are tested against benchmarks with labelled sentences containing tagged entities, and require important pre-training and fine-tuning on task-specific data. However, in a real use-case scenario such as in a newspaper company mostly dedicated to local information, relations are of varied, highly specific type, with virtually no annotated data for such relations, and many entities co-occur in a sentence without being related. We question the use of supervised state-of-the-art models in such a context, where resources such as time, computing power and human annotators are limited. To adapt to these constraints, we experiment with an active-learning based relation extraction pipeline, consisting of a binary LSTM-based lightweight model for detecting the relations that do exist, and a state-of-the-art model for relation classification. We compare several choices for classification models in this scenario, from basic word embedding averaging, to graph neural networks and Bert-based ones, as well as several active learning acquisition strategies, in order to find the most cost-efficient yet accurate approach in our French largest daily newspaper company’s use case.
%U https://aclanthology.org/2021.ranlp-1.101
%P 886-894
Markdown (Informal)
[Active Learning for Interactive Relation Extraction in a French Newspaper’s Articles](https://aclanthology.org/2021.ranlp-1.101) (Mallart et al., RANLP 2021)
ACL