@inproceedings{el-khbir-etal-2024-information-extraction,
title = "Information Extraction with Differentiable Beam Search on Graph {RNN}s",
author = "El Khbir, Niama and
Tomeh, Nadi and
Charnois, Thierry",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.796",
pages = "9084--9096",
abstract = "Information extraction (IE) from text documents is an important NLP task that includes entity, relation, and event extraction. These tasks are often addressed jointly as a graph generation problem, where entities and event triggers represent nodes and where relations and event arguments represent edges. Most existing systems use local classifiers for nodes and edges, trained using cross-entropy loss, and employ inference strategies such as beam search to approximate the optimal graph structure. These approaches typically suffer from exposure bias due to the discrepancy between training and decoding. In this paper, we tackle this problem by casting graph generation as auto-regressive sequence labeling and making its training aware of the decoding procedure by using a differentiable version of beam search. We evaluate the effectiveness of our approach through extensive experiments conducted on the ACE05 and ConLL04 datasets across diverse languages. Our experimental findings affirm that our model outperforms its non-decoding-aware version for all datasets employed. Furthermore, we conduct ablation studies that emphasize the effectiveness of aligning training and inference. Additionally, we introduce a novel quantification of exposure bias within this context, providing valuable insights into the functioning of our model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-khbir-etal-2024-information-extraction">
<titleInfo>
<title>Information Extraction with Differentiable Beam Search on Graph RNNs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niama</namePart>
<namePart type="family">El Khbir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Charnois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information extraction (IE) from text documents is an important NLP task that includes entity, relation, and event extraction. These tasks are often addressed jointly as a graph generation problem, where entities and event triggers represent nodes and where relations and event arguments represent edges. Most existing systems use local classifiers for nodes and edges, trained using cross-entropy loss, and employ inference strategies such as beam search to approximate the optimal graph structure. These approaches typically suffer from exposure bias due to the discrepancy between training and decoding. In this paper, we tackle this problem by casting graph generation as auto-regressive sequence labeling and making its training aware of the decoding procedure by using a differentiable version of beam search. We evaluate the effectiveness of our approach through extensive experiments conducted on the ACE05 and ConLL04 datasets across diverse languages. Our experimental findings affirm that our model outperforms its non-decoding-aware version for all datasets employed. Furthermore, we conduct ablation studies that emphasize the effectiveness of aligning training and inference. Additionally, we introduce a novel quantification of exposure bias within this context, providing valuable insights into the functioning of our model.</abstract>
<identifier type="citekey">el-khbir-etal-2024-information-extraction</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.796</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9084</start>
<end>9096</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Information Extraction with Differentiable Beam Search on Graph RNNs
%A El Khbir, Niama
%A Tomeh, Nadi
%A Charnois, Thierry
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F el-khbir-etal-2024-information-extraction
%X Information extraction (IE) from text documents is an important NLP task that includes entity, relation, and event extraction. These tasks are often addressed jointly as a graph generation problem, where entities and event triggers represent nodes and where relations and event arguments represent edges. Most existing systems use local classifiers for nodes and edges, trained using cross-entropy loss, and employ inference strategies such as beam search to approximate the optimal graph structure. These approaches typically suffer from exposure bias due to the discrepancy between training and decoding. In this paper, we tackle this problem by casting graph generation as auto-regressive sequence labeling and making its training aware of the decoding procedure by using a differentiable version of beam search. We evaluate the effectiveness of our approach through extensive experiments conducted on the ACE05 and ConLL04 datasets across diverse languages. Our experimental findings affirm that our model outperforms its non-decoding-aware version for all datasets employed. Furthermore, we conduct ablation studies that emphasize the effectiveness of aligning training and inference. Additionally, we introduce a novel quantification of exposure bias within this context, providing valuable insights into the functioning of our model.
%U https://aclanthology.org/2024.lrec-main.796
%P 9084-9096
Markdown (Informal)
[Information Extraction with Differentiable Beam Search on Graph RNNs](https://aclanthology.org/2024.lrec-main.796) (El Khbir et al., LREC-COLING 2024)
ACL