@inproceedings{gong-eldardiry-2024-shot-relation,
title = "Few-Shot Relation Extraction with Hybrid Visual Evidence",
author = "Gong, Jiaying and
Eldardiry, Hoda",
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.635",
pages = "7232--7247",
abstract = "The goal of few-shot relation extraction is to predict relations between name entities in a sentence when only a few labeled instances are available for training. Existing few-shot relation extraction methods focus on uni-modal information such as text only. This reduces performance when there is no clear contexts between the name entities described in text. We propose a multi-modal few-shot relation extraction model (MFS-HVE) that leverages both textual and visual semantic information to learn a multi-modal representation jointly. The MFS-HVE includes semantic feature extractors and multi-modal fusion components. The MFS-HVE semantic feature extractors are developed to extract both textual and visual features. The visual features include global image features and local object features within the image. The MFS-HVE multi-modal fusion unit integrates information from various modalities using image-guided attention, object-guided attention, and hybrid feature attention to fully capture the semantic interaction between visual regions of images and relevant texts. Extensive experiments conducted on two public datasets demonstrate that semantic visual information significantly improves performance of few-shot relation prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-eldardiry-2024-shot-relation">
<titleInfo>
<title>Few-Shot Relation Extraction with Hybrid Visual Evidence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaying</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoda</namePart>
<namePart type="family">Eldardiry</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>The goal of few-shot relation extraction is to predict relations between name entities in a sentence when only a few labeled instances are available for training. Existing few-shot relation extraction methods focus on uni-modal information such as text only. This reduces performance when there is no clear contexts between the name entities described in text. We propose a multi-modal few-shot relation extraction model (MFS-HVE) that leverages both textual and visual semantic information to learn a multi-modal representation jointly. The MFS-HVE includes semantic feature extractors and multi-modal fusion components. The MFS-HVE semantic feature extractors are developed to extract both textual and visual features. The visual features include global image features and local object features within the image. The MFS-HVE multi-modal fusion unit integrates information from various modalities using image-guided attention, object-guided attention, and hybrid feature attention to fully capture the semantic interaction between visual regions of images and relevant texts. Extensive experiments conducted on two public datasets demonstrate that semantic visual information significantly improves performance of few-shot relation prediction.</abstract>
<identifier type="citekey">gong-eldardiry-2024-shot-relation</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.635</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7232</start>
<end>7247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Few-Shot Relation Extraction with Hybrid Visual Evidence
%A Gong, Jiaying
%A Eldardiry, Hoda
%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 gong-eldardiry-2024-shot-relation
%X The goal of few-shot relation extraction is to predict relations between name entities in a sentence when only a few labeled instances are available for training. Existing few-shot relation extraction methods focus on uni-modal information such as text only. This reduces performance when there is no clear contexts between the name entities described in text. We propose a multi-modal few-shot relation extraction model (MFS-HVE) that leverages both textual and visual semantic information to learn a multi-modal representation jointly. The MFS-HVE includes semantic feature extractors and multi-modal fusion components. The MFS-HVE semantic feature extractors are developed to extract both textual and visual features. The visual features include global image features and local object features within the image. The MFS-HVE multi-modal fusion unit integrates information from various modalities using image-guided attention, object-guided attention, and hybrid feature attention to fully capture the semantic interaction between visual regions of images and relevant texts. Extensive experiments conducted on two public datasets demonstrate that semantic visual information significantly improves performance of few-shot relation prediction.
%U https://aclanthology.org/2024.lrec-main.635
%P 7232-7247
Markdown (Informal)
[Few-Shot Relation Extraction with Hybrid Visual Evidence](https://aclanthology.org/2024.lrec-main.635) (Gong & Eldardiry, LREC-COLING 2024)
ACL
- Jiaying Gong and Hoda Eldardiry. 2024. Few-Shot Relation Extraction with Hybrid Visual Evidence. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7232–7247, Torino, Italia. ELRA and ICCL.