University of Sussex
Browse
cvsc2014.pdf (209.96 kB)

Distributional composition using higher-order dependency vectors

Download (209.96 kB)
conference contribution
posted on 2023-06-09, 00:13 authored by Julie WeedsJulie Weeds, David WeirDavid Weir, Jeremy ReffinJeremy Reffin
This paper concerns how to apply compositional methods to vectors based on grammatical dependency relation vectors. We demonstrate the potential of a novel approach which uses higher-order grammatical dependency relations as features. We apply the approach to adjective-noun compounds with promising results in the prediction of the vectors for (held-out) observed phrases.

History

Publication status

  • Published

File Version

  • Published version

Journal

Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC)

Publisher

Association for Computational Linguistics (ACL)

Page range

11-20

Event name

2nd Workshop on Continuous Space Vector Models and their Composition (EACL 2014 Workshop)

Event location

Gothenberg, Sweden

Event type

conference

Event date

April 26-30, 2014

Department affiliated with

  • Informatics Publications

Notes

W14-1502

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2016-02-05

First Open Access (FOA) Date

2016-02-05

First Compliant Deposit (FCD) Date

2016-02-05

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC