Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary

Jayant Krishnamurthy, Tom M. Mitchell


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.
Anthology ID:
Q15-1019
Volume:
Transactions of the Association for Computational Linguistics, Volume 3
Month:
Year:
2015
Address:
Venue:
TACL
SIG:
Publisher:
Note:
Pages:
257–270
Language:
URL:
https://www.aclweb.org/anthology/Q15-1019
DOI:
10.1162/tacl_a_00137
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/Q15-1019.pdf
Video:
 https://techtalks.tv/talks/learning-a-compositional-semantics-for-freebase-with-an-open-predicate-vocabulary/61714/