Graph-based Syntactic Word Embeddings

Ragheb Al-Ghezi, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

3 Downloads (Pure)

Abstract

We propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees. Using biased random walk methods, our embeddings not only encode syntactic information about words, but they also capture contextual information. We also propose a method to train the embeddings on multiple constituency parse trees to ensure the encoding of global syntactic representation. Quantitative evaluation of the embeddings shows competitive performance on POS tagging task when compared to other types of embeddings, and qualitative evaluation reveals interesting facts about the syntactic typology learned by these embeddings.
Original languageEnglish
Title of host publicationProceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
Pages72–78
Number of pages7
ISBN (Electronic)978-1-952148-42-2
Publication statusPublished - 30 Dec 2020
MoE publication typeA4 Article in a conference publication
EventWorkshop on Graph-Based Methods for Natural Language Processing - Barcelona, Spain
Duration: 13 Dec 202013 Dec 2020

Workshop

WorkshopWorkshop on Graph-Based Methods for Natural Language Processing
Abbreviated titleTextGraphs
CountrySpain
CityBarcelona
Period13/12/202013/12/2020

Fingerprint Dive into the research topics of 'Graph-based Syntactic Word Embeddings'. Together they form a unique fingerprint.

Cite this