University of Sussex
2021.findings-acl.296.pdf (1.18 MB)

Representing syntax and composition with geometric transformations

Download (1.18 MB)
conference contribution
posted on 2023-06-12, 09:52 authored by Lorenzo Scott Bertolini, Julie WeedsJulie Weeds, David WeirDavid Weir, Qiwei PengQiwei Peng
The exploitation of syntactic graphs (SyGs) as a word's context has been shown to be beneficial for distributional semantic models (DSMs), both at the level of individual word representations and in deriving phrasal representations via composition. However, notwithstanding the potential performance benefit, the syntactically-aware DSMs proposed to date have huge numbers of parameters (compared to conventional DSMs) and suffer from data sparsity. Furthermore, the encoding of the SyG links (i.e., the syntactic relations) has been largely limited to linear maps. The knowledge graphs' literature, on the other hand, has proposed light-weight models employing different geometric transformations (GTs) to encode edges in a knowledge graph (KG). Our work explores the possibility of adopting this family of models to encode SyGs. Furthermore, we investigate which GT better encodes syntactic relations, so that these representations can be used to enhance phrase-level composition via syntactic contextualisation.


Publication status

  • Published

File Version

  • Published version


Findings of the Association for Computational Linguistics: ACL 2021


Association for Computational Linguistics

Page range


Event name

The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021)

Event location

Bangkok, Thailand

Event type


Event date

August 1-6, 2021

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date


First Open Access (FOA) Date


First Compliant Deposit (FCD) Date


Usage metrics

    University of Sussex (Publications)


    No categories selected