Quantifying the morphosyntactic content of Brown Clusters

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

1 Citationer (Scopus)
228 Downloads (Pure)

Abstract

Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing (NLP) systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable of distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms' optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features.

OriginalsprogEngelsk
TitelLong and Short Papers : Human Language Technologies
RedaktørerJill Burstein, Christy Doran, Thamar Solorio
Antal sider10
Vol/bind1
UdgivelsesstedStroudsburg, PA
ForlagAssociation for Computational Linguistics
Publikationsdato2019
Sider1541-1550
ISBN (Trykt)978-1-950737-13-0
ISBN (Elektronisk)9781950737130
StatusUdgivet - 2019
BegivenhedAnnual Conference of the North American Chapter of the Association for Computational Linguistics - Hyatt Regency, Minneapolis, USA
Varighed: 3 jun. 20195 jun. 2019
https://naacl2019.org

Konference

KonferenceAnnual Conference of the North American Chapter of the Association for Computational Linguistics
LokationHyatt Regency
Land/OmrådeUSA
ByMinneapolis
Periode03/06/201905/06/2019
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Quantifying the morphosyntactic content of Brown Clusters'. Sammen danner de et unikt fingeraftryk.

Citationsformater