@article{krishnamurthy-mitchell-2015-learning,
title = "Learning a Compositional Semantics for {F}reebase with an Open Predicate Vocabulary",
author = "Krishnamurthy, Jayant and
Mitchell, Tom M.",
editor = "Collins, Michael and
Lee, Lillian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "3",
year = "2015",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q15-1019",
doi = "10.1162/tacl_a_00137",
pages = "257--270",
abstract = "We present an approach to learning a model-theoretic semantics for natural language tied to Freebase. Crucially, our approach uses an open predicate vocabulary, enabling it to produce denotations for phrases such as {``}Republican front-runner from Texas{''} whose semantics cannot be represented using the Freebase schema. Our approach directly converts a sentence{'}s syntactic CCG parse into a logical form containing predicates derived from the words in the sentence, assigning each word a consistent semantics across sentences. This logical form is evaluated against a learned probabilistic database that defines a distribution over denotations for each textual predicate. A training phase produces this probabilistic database using a corpus of entity-linked text and probabilistic matrix factorization with a novel ranking objective function. We evaluate our approach on a compositional question answering task where it outperforms several competitive baselines. We also compare our approach against manually annotated Freebase queries, finding that our open predicate vocabulary enables us to answer many questions that Freebase cannot.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnamurthy-mitchell-2015-learning">
<titleInfo>
<title>Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jayant</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mitchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2015</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We present an approach to learning a model-theoretic semantics for natural language tied to Freebase. Crucially, our approach uses an open predicate vocabulary, enabling it to produce denotations for phrases such as “Republican front-runner from Texas” whose semantics cannot be represented using the Freebase schema. Our approach directly converts a sentence’s syntactic CCG parse into a logical form containing predicates derived from the words in the sentence, assigning each word a consistent semantics across sentences. This logical form is evaluated against a learned probabilistic database that defines a distribution over denotations for each textual predicate. A training phase produces this probabilistic database using a corpus of entity-linked text and probabilistic matrix factorization with a novel ranking objective function. We evaluate our approach on a compositional question answering task where it outperforms several competitive baselines. We also compare our approach against manually annotated Freebase queries, finding that our open predicate vocabulary enables us to answer many questions that Freebase cannot.</abstract>
<identifier type="citekey">krishnamurthy-mitchell-2015-learning</identifier>
<identifier type="doi">10.1162/tacl_a_00137</identifier>
<location>
<url>https://aclanthology.org/Q15-1019</url>
</location>
<part>
<date>2015</date>
<detail type="volume"><number>3</number></detail>
<extent unit="page">
<start>257</start>
<end>270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary
%A Krishnamurthy, Jayant
%A Mitchell, Tom M.
%J Transactions of the Association for Computational Linguistics
%D 2015
%V 3
%I MIT Press
%C Cambridge, MA
%F krishnamurthy-mitchell-2015-learning
%X We present an approach to learning a model-theoretic semantics for natural language tied to Freebase. Crucially, our approach uses an open predicate vocabulary, enabling it to produce denotations for phrases such as “Republican front-runner from Texas” whose semantics cannot be represented using the Freebase schema. Our approach directly converts a sentence’s syntactic CCG parse into a logical form containing predicates derived from the words in the sentence, assigning each word a consistent semantics across sentences. This logical form is evaluated against a learned probabilistic database that defines a distribution over denotations for each textual predicate. A training phase produces this probabilistic database using a corpus of entity-linked text and probabilistic matrix factorization with a novel ranking objective function. We evaluate our approach on a compositional question answering task where it outperforms several competitive baselines. We also compare our approach against manually annotated Freebase queries, finding that our open predicate vocabulary enables us to answer many questions that Freebase cannot.
%R 10.1162/tacl_a_00137
%U https://aclanthology.org/Q15-1019
%U https://doi.org/10.1162/tacl_a_00137
%P 257-270
Markdown (Informal)
[Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary](https://aclanthology.org/Q15-1019) (Krishnamurthy & Mitchell, TACL 2015)
ACL