Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach

Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-06
Main Authors: Arthur Colombini Gusmão, Alvaro Henrique Chaim Correia, Glauber De Bona, Fabio Gagliardi Cozman
Format: Article
Language:English
Subjects:
Embedding
Knowledge base
Model accuracy
Natural language processing
Neural networks
Pedagogy
Semantic web
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Arthur Colombini Gusmão
Alvaro Henrique Chaim Correia
Glauber De Bona
Fabio Gagliardi Cozman
description Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt "pedagogical approaches" (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2074054392</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2074054392</sourcerecordid><originalsourceid>FETCH-proquest_journals_20740543923</originalsourceid><addsrcrecordid>eNqNitEKgjAUQEcQJOU_XOhZWJtm9WZhGBH00Lssd13K2mxT-v0M-oCezoFzJiRgnK-iTczYjITet5RStk5ZkvCAFCfTo-sc9o1RkD_vKOXXLlai9mBrOBv71igVwl549DvI4IpSKKuaSmjIus5ZUT0WZFoL7TH8cU6Wx_x2KKIxvwb0fdnawZkxlYymMU1ivmX8v-sD-nI7Tw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2074054392</pqid></control><display><type>article</type><title>Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach</title><source>Publicly Available Content (ProQuest)</source><creator>Arthur Colombini Gusmão ; Alvaro Henrique Chaim Correia ; Glauber De Bona ; Fabio Gagliardi Cozman</creator><creatorcontrib>Arthur Colombini Gusmão ; Alvaro Henrique Chaim Correia ; Glauber De Bona ; Fabio Gagliardi Cozman</creatorcontrib><description>Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt "pedagogical approaches" (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Embedding ; Knowledge base ; Model accuracy ; Natural language processing ; Neural networks ; Pedagogy ; Semantic web</subject><ispartof>arXiv.org, 2018-06</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2074054392?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Arthur Colombini Gusmão</creatorcontrib><creatorcontrib>Alvaro Henrique Chaim Correia</creatorcontrib><creatorcontrib>Glauber De Bona</creatorcontrib><creatorcontrib>Fabio Gagliardi Cozman</creatorcontrib><title>Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach</title><title>arXiv.org</title><description>Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt "pedagogical approaches" (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.</description><subject>Embedding</subject><subject>Knowledge base</subject><subject>Model accuracy</subject><subject>Natural language processing</subject><subject>Neural networks</subject><subject>Pedagogy</subject><subject>Semantic web</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNitEKgjAUQEcQJOU_XOhZWJtm9WZhGBH00Lssd13K2mxT-v0M-oCezoFzJiRgnK-iTczYjITet5RStk5ZkvCAFCfTo-sc9o1RkD_vKOXXLlai9mBrOBv71igVwl549DvI4IpSKKuaSmjIus5ZUT0WZFoL7TH8cU6Wx_x2KKIxvwb0fdnawZkxlYymMU1ivmX8v-sD-nI7Tw</recordid><startdate>20180620</startdate><enddate>20180620</enddate><creator>Arthur Colombini Gusmão</creator><creator>Alvaro Henrique Chaim Correia</creator><creator>Glauber De Bona</creator><creator>Fabio Gagliardi Cozman</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20180620</creationdate><title>Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach</title><author>Arthur Colombini Gusmão ; Alvaro Henrique Chaim Correia ; Glauber De Bona ; Fabio Gagliardi Cozman</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20740543923</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Embedding</topic><topic>Knowledge base</topic><topic>Model accuracy</topic><topic>Natural language processing</topic><topic>Neural networks</topic><topic>Pedagogy</topic><topic>Semantic web</topic><toplevel>online_resources</toplevel><creatorcontrib>Arthur Colombini Gusmão</creatorcontrib><creatorcontrib>Alvaro Henrique Chaim Correia</creatorcontrib><creatorcontrib>Glauber De Bona</creatorcontrib><creatorcontrib>Fabio Gagliardi Cozman</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Engineering Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Arthur Colombini Gusmão</au><au>Alvaro Henrique Chaim Correia</au><au>Glauber De Bona</au><au>Fabio Gagliardi Cozman</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach</atitle><jtitle>arXiv.org</jtitle><date>2018-06-20</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. In this paper, we adapt "pedagogical approaches" (from the literature on neural networks) so as to interpret embedding models by extracting weighted Horn rules from them. We show how pedagogical approaches have to be adapted to take upon the large-scale relational aspects of knowledge bases and show experimentally their strengths and weaknesses.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_2074054392
source Publicly Available Content (ProQuest)
subjects Embedding
Knowledge base
Model accuracy
Natural language processing
Neural networks
Pedagogy
Semantic web
title Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T18%3A49%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Interpreting%20Embedding%20Models%20of%20Knowledge%20Bases:%20A%20Pedagogical%20Approach&rft.jtitle=arXiv.org&rft.au=Arthur%20Colombini%20Gusm%C3%A3o&rft.date=2018-06-20&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2074054392%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20740543923%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2074054392&rft_id=info:pmid/&rfr_iscdi=true