@inproceedings{thejas-etal-2019-text,
title = "Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases",
author = "Thejas, V and
Gupta, Abhijeet and
Pad{\'o}, Sebastian",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1137",
doi = "10.26615/978-954-452-056-4_137",
pages = "1194--1202",
abstract = "Collaboratively constructed knowledge bases play an important role in information systems, but are essentially always incomplete. Thus, a large number of models has been developed for Knowledge Base Completion, the task of predicting new attributes of entities given partial descriptions of these entities. Virtually all of these models either concentrate on numeric attributes ({\textless}Italy,GDP,2T{\$}{\textgreater}) or they concentrate on categorical attributes ({\textless}Tim Cook,chairman,Apple{\textgreater}). In this paper, we propose a simple feed-forward neural architecture to jointly predict numeric and categorical attributes based on embeddings learned from textual occurrences of the entities in question. Following insights from multi-task learning, our hypothesis is that due to the correlations among attributes of different kinds, joint prediction improves over separate prediction. Our experiments on seven FreeBase domains show that this hypothesis is true of the two attribute types: we find substantial improvements for numeric attributes in the joint model, while performance remains largely unchanged for categorical attributes. Our analysis indicates that this is the case because categorical attributes, many of which describe membership in various classes, provide useful {`}background knowledge{'} for numeric prediction, while this is true to a lesser degree in the inverse direction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thejas-etal-2019-text">
<titleInfo>
<title>Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases</title>
</titleInfo>
<name type="personal">
<namePart type="given">V</namePart>
<namePart type="family">Thejas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhijeet</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collaboratively constructed knowledge bases play an important role in information systems, but are essentially always incomplete. Thus, a large number of models has been developed for Knowledge Base Completion, the task of predicting new attributes of entities given partial descriptions of these entities. Virtually all of these models either concentrate on numeric attributes (\textlessItaly,GDP,2T$\textgreater) or they concentrate on categorical attributes (\textlessTim Cook,chairman,Apple\textgreater). In this paper, we propose a simple feed-forward neural architecture to jointly predict numeric and categorical attributes based on embeddings learned from textual occurrences of the entities in question. Following insights from multi-task learning, our hypothesis is that due to the correlations among attributes of different kinds, joint prediction improves over separate prediction. Our experiments on seven FreeBase domains show that this hypothesis is true of the two attribute types: we find substantial improvements for numeric attributes in the joint model, while performance remains largely unchanged for categorical attributes. Our analysis indicates that this is the case because categorical attributes, many of which describe membership in various classes, provide useful ‘background knowledge’ for numeric prediction, while this is true to a lesser degree in the inverse direction.</abstract>
<identifier type="citekey">thejas-etal-2019-text</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_137</identifier>
<location>
<url>https://aclanthology.org/R19-1137</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>1194</start>
<end>1202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases
%A Thejas, V.
%A Gupta, Abhijeet
%A Padó, Sebastian
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F thejas-etal-2019-text
%X Collaboratively constructed knowledge bases play an important role in information systems, but are essentially always incomplete. Thus, a large number of models has been developed for Knowledge Base Completion, the task of predicting new attributes of entities given partial descriptions of these entities. Virtually all of these models either concentrate on numeric attributes (\textlessItaly,GDP,2T$\textgreater) or they concentrate on categorical attributes (\textlessTim Cook,chairman,Apple\textgreater). In this paper, we propose a simple feed-forward neural architecture to jointly predict numeric and categorical attributes based on embeddings learned from textual occurrences of the entities in question. Following insights from multi-task learning, our hypothesis is that due to the correlations among attributes of different kinds, joint prediction improves over separate prediction. Our experiments on seven FreeBase domains show that this hypothesis is true of the two attribute types: we find substantial improvements for numeric attributes in the joint model, while performance remains largely unchanged for categorical attributes. Our analysis indicates that this is the case because categorical attributes, many of which describe membership in various classes, provide useful ‘background knowledge’ for numeric prediction, while this is true to a lesser degree in the inverse direction.
%R 10.26615/978-954-452-056-4_137
%U https://aclanthology.org/R19-1137
%U https://doi.org/10.26615/978-954-452-056-4_137
%P 1194-1202
Markdown (Informal)
[Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases](https://aclanthology.org/R19-1137) (Thejas et al., RANLP 2019)
ACL