@inproceedings{mavromatis-karypis-2022-rearev,
title = "{R}ea{R}ev: Adaptive Reasoning for Question Answering over Knowledge Graphs",
author = "Mavromatis, Costas and
Karypis, George",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.181",
doi = "10.18653/v1/2022.findings-emnlp.181",
pages = "2447--2458",
abstract = "Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Graph (KG) using natural language queries. The challenge is to learn to reason over question-relevant KG facts that traverse KG entities and lead to the question answers. To facilitate reasoning, the question is decoded into instructions, which are dense question representations used to guide the KG traversals. However, if the derived instructions do not exactly match the underlying KG information, they may lead to reasoning under irrelevant context. Our method, termed ReaRev, introduces a new way to KGQA reasoning with respectto both instruction decoding and execution. To improve instruction decoding, we perform reasoning in an adaptive manner, where KG-aware information is used to iteratively update the initial instructions. To improve instruction execution, we emulate breadth-first search (BFS) with graph neural networks (GNNs). The BFS strategy treats the instructions as a set and allows our method to decide on their execution order on the fly. Experimental results on three KGQA benchmarks demonstrate the ReaRev{'}s effectiveness compared with previous state-of-the-art, especially when the KG is incomplete or when we tackle complex questions. Our code is publicly available at \url{https://github.com/cmavro/ReaRev_KGQA}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mavromatis-karypis-2022-rearev">
<titleInfo>
<title>ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Costas</namePart>
<namePart type="family">Mavromatis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Karypis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Graph (KG) using natural language queries. The challenge is to learn to reason over question-relevant KG facts that traverse KG entities and lead to the question answers. To facilitate reasoning, the question is decoded into instructions, which are dense question representations used to guide the KG traversals. However, if the derived instructions do not exactly match the underlying KG information, they may lead to reasoning under irrelevant context. Our method, termed ReaRev, introduces a new way to KGQA reasoning with respectto both instruction decoding and execution. To improve instruction decoding, we perform reasoning in an adaptive manner, where KG-aware information is used to iteratively update the initial instructions. To improve instruction execution, we emulate breadth-first search (BFS) with graph neural networks (GNNs). The BFS strategy treats the instructions as a set and allows our method to decide on their execution order on the fly. Experimental results on three KGQA benchmarks demonstrate the ReaRev’s effectiveness compared with previous state-of-the-art, especially when the KG is incomplete or when we tackle complex questions. Our code is publicly available at https://github.com/cmavro/ReaRev_KGQA.</abstract>
<identifier type="citekey">mavromatis-karypis-2022-rearev</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.181</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.181</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2447</start>
<end>2458</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
%A Mavromatis, Costas
%A Karypis, George
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F mavromatis-karypis-2022-rearev
%X Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Graph (KG) using natural language queries. The challenge is to learn to reason over question-relevant KG facts that traverse KG entities and lead to the question answers. To facilitate reasoning, the question is decoded into instructions, which are dense question representations used to guide the KG traversals. However, if the derived instructions do not exactly match the underlying KG information, they may lead to reasoning under irrelevant context. Our method, termed ReaRev, introduces a new way to KGQA reasoning with respectto both instruction decoding and execution. To improve instruction decoding, we perform reasoning in an adaptive manner, where KG-aware information is used to iteratively update the initial instructions. To improve instruction execution, we emulate breadth-first search (BFS) with graph neural networks (GNNs). The BFS strategy treats the instructions as a set and allows our method to decide on their execution order on the fly. Experimental results on three KGQA benchmarks demonstrate the ReaRev’s effectiveness compared with previous state-of-the-art, especially when the KG is incomplete or when we tackle complex questions. Our code is publicly available at https://github.com/cmavro/ReaRev_KGQA.
%R 10.18653/v1/2022.findings-emnlp.181
%U https://aclanthology.org/2022.findings-emnlp.181
%U https://doi.org/10.18653/v1/2022.findings-emnlp.181
%P 2447-2458
Markdown (Informal)
[ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs](https://aclanthology.org/2022.findings-emnlp.181) (Mavromatis & Karypis, Findings 2022)
ACL