@inproceedings{wang-etal-2024-hypermr-hyperbolic,
title = "{H}yper{MR}: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering",
author = "Wang, Bin and
Xu, Fuyong and
Liu, Peiyu and
Zhu, Zhenfang",
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.746",
pages = "8505--8515",
abstract = "Knowledge-based Visual Question Answering (KBVQA) is a challenging task, which aims to answer an image related question based on external knowledge. Most of the works describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge graphs with hierarchical and scale-free structure in KBVQA, and limits the multi-hop reasoning capability of the model. In contrast, the hyperbolic space shows exciting prospects for low-distortion embedding of graphs with hierarchical and free-scale structure. In addition, we map the different stages of reasoning into multiple adjustable hyperbolic spaces, achieving low-distortion, fine-grained reasoning. Extensive experiments on the KVQA, PQ and PQL datasets demonstrate the effectiveness of HyperMR for strong-hierarchy knowledge graphs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-hypermr-hyperbolic">
<titleInfo>
<title>HyperMR: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuyong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenfang</namePart>
<namePart type="family">Zhu</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>Knowledge-based Visual Question Answering (KBVQA) is a challenging task, which aims to answer an image related question based on external knowledge. Most of the works describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge graphs with hierarchical and scale-free structure in KBVQA, and limits the multi-hop reasoning capability of the model. In contrast, the hyperbolic space shows exciting prospects for low-distortion embedding of graphs with hierarchical and free-scale structure. In addition, we map the different stages of reasoning into multiple adjustable hyperbolic spaces, achieving low-distortion, fine-grained reasoning. Extensive experiments on the KVQA, PQ and PQL datasets demonstrate the effectiveness of HyperMR for strong-hierarchy knowledge graphs.</abstract>
<identifier type="citekey">wang-etal-2024-hypermr-hyperbolic</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.746</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8505</start>
<end>8515</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HyperMR: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering
%A Wang, Bin
%A Xu, Fuyong
%A Liu, Peiyu
%A Zhu, Zhenfang
%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 wang-etal-2024-hypermr-hyperbolic
%X Knowledge-based Visual Question Answering (KBVQA) is a challenging task, which aims to answer an image related question based on external knowledge. Most of the works describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge graphs with hierarchical and scale-free structure in KBVQA, and limits the multi-hop reasoning capability of the model. In contrast, the hyperbolic space shows exciting prospects for low-distortion embedding of graphs with hierarchical and free-scale structure. In addition, we map the different stages of reasoning into multiple adjustable hyperbolic spaces, achieving low-distortion, fine-grained reasoning. Extensive experiments on the KVQA, PQ and PQL datasets demonstrate the effectiveness of HyperMR for strong-hierarchy knowledge graphs.
%U https://aclanthology.org/2024.lrec-main.746
%P 8505-8515
Markdown (Informal)
[HyperMR: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering](https://aclanthology.org/2024.lrec-main.746) (Wang et al., LREC-COLING 2024)
ACL