Crosslingual and Multilingual Construction of Syntax-Based Vector Space Models

Syntax-based distributional models of lexical semantics provide a flexible and linguistically adequate representation of co-occurrence information. However, their construction requires large, accurately parsed corpora, which are unavailable for most languages. In this paper, we develop a number of m...

Full description

Saved in:
Bibliographic Details
Published in:Transactions of the Association for Computational Linguistics Vol. 2; pp. 245 - 258
Main Authors: Utt, Jason, Padó, Sebastian
Format: Journal Article
Language:English
Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.03.2021
MIT Press Journals, The
The MIT Press
Subjects:
Benchmarks
Comorbidity
Computational linguistics
English language
German language
Languages
Lexical semantics
Model accuracy
Monolingualism
Semantics
Serbo-Croatian language
Syntactic structures
Syntax
Vector spaces
ISSN:2307-387X, 2307-387X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Syntax-based distributional models of lexical semantics provide a flexible and linguistically adequate representation of co-occurrence information. However, their construction requires large, accurately parsed corpora, which are unavailable for most languages. In this paper, we develop a number of methods to overcome this obstacle. We describe (a) a approach that constructs a syntax-based model for a new language requiring only an English resource and a translation lexicon; and (b) approaches that combine crosslingual with monolingual information, subject to availability. We evaluate on two lexical semantic benchmarks in German and Croatian. We find that the models exhibit complementary profiles: crosslingual models yield higher accuracies while monolingual models provide better coverage. In addition, we show that simple multilingual models can successfully combine their strengths.
Bibliography:Volume, 2014
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2307-387X
2307-387X
DOI:10.1162/tacl_a_00180