@inproceedings{das-etal-2017-chains,
title = "Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks",
author = "Das, Rajarshi and
Neelakantan, Arvind and
Belanger, David and
McCallum, Andrew",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-1013/",
pages = "132--141",
abstract = "Our goal is to combine the rich multi-step inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and relations in text and large-scale knowledge bases (KBs). Neelakantan et al. (2015) use RNNs to compose the distributed semantics of multi-hop paths in KBs; however for multiple reasons, the approach lacks accuracy and practicality. This paper proposes three significant modeling advances: (1) we learn to jointly reason about relations, \textit{entities, and entity-types}; (2) we use neural attention modeling to incorporate \textit{multiple paths}; (3) we learn to \textit{share strength in a single RNN} that represents logical composition across all relations. On a large-scale Freebase+ClueWeb prediction task, we achieve 25{\%} error reduction, and a 53{\%} error reduction on sparse relations due to shared strength. On chains of reasoning in WordNet we reduce error in mean quantile by 84{\%} versus previous state-of-the-art."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2017-chains">
<titleInfo>
<title>Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajarshi</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvind</namePart>
<namePart type="family">Neelakantan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Belanger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our goal is to combine the rich multi-step inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and relations in text and large-scale knowledge bases (KBs). Neelakantan et al. (2015) use RNNs to compose the distributed semantics of multi-hop paths in KBs; however for multiple reasons, the approach lacks accuracy and practicality. This paper proposes three significant modeling advances: (1) we learn to jointly reason about relations, entities, and entity-types; (2) we use neural attention modeling to incorporate multiple paths; (3) we learn to share strength in a single RNN that represents logical composition across all relations. On a large-scale Freebase+ClueWeb prediction task, we achieve 25% error reduction, and a 53% error reduction on sparse relations due to shared strength. On chains of reasoning in WordNet we reduce error in mean quantile by 84% versus previous state-of-the-art.</abstract>
<identifier type="citekey">das-etal-2017-chains</identifier>
<location>
<url>https://aclanthology.org/E17-1013/</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>132</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks
%A Das, Rajarshi
%A Neelakantan, Arvind
%A Belanger, David
%A McCallum, Andrew
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F das-etal-2017-chains
%X Our goal is to combine the rich multi-step inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and relations in text and large-scale knowledge bases (KBs). Neelakantan et al. (2015) use RNNs to compose the distributed semantics of multi-hop paths in KBs; however for multiple reasons, the approach lacks accuracy and practicality. This paper proposes three significant modeling advances: (1) we learn to jointly reason about relations, entities, and entity-types; (2) we use neural attention modeling to incorporate multiple paths; (3) we learn to share strength in a single RNN that represents logical composition across all relations. On a large-scale Freebase+ClueWeb prediction task, we achieve 25% error reduction, and a 53% error reduction on sparse relations due to shared strength. On chains of reasoning in WordNet we reduce error in mean quantile by 84% versus previous state-of-the-art.
%U https://aclanthology.org/E17-1013/
%P 132-141
Markdown (Informal)
[Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks](https://aclanthology.org/E17-1013/) (Das et al., EACL 2017)
- Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks (Das et al., EACL 2017)
ACL
- Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum. 2017. Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 132–141, Valencia, Spain. Association for Computational Linguistics.