Uproszczony widok
Użyj poniższego opisu do cytowania zasobu albo wyeksportuj go w wybranym formacie:
Janz, Arkadiusz; Piasecki, Maciej and Wątorski, Piotr, 2021, Neural Language Models vs Wordnet-based Semantically Enriched Representation in CST Relation Recognition, CLARIN-PL Repository, http://hdl.handle.net/11321/981.
Udostępnij
dc.contributor.authorJanz, Arkadiusz
dc.contributor.authorPiasecki, Maciej
dc.contributor.authorWątorski, Piotr
dc.date.accessioned2025-12-17T10:23:42Z
dc.date.available2025-12-17T10:23:42Z
dc.date.issued2021-01-01
dc.descriptionNeural language models, including transformer-based models, that are pretrained on very large corpora became a common way to represent text in various tasks, including recognition of textual semantic relations, e.g. Cross-document Structure Theory. Pretrained models are usually fine tuned to downstream tasks and the obtained vectors are used as an input for deep neural classifiers. No linguistic knowledge obtained from resources and tools is utilised. In this paper we compare such universal approaches with a combination of rich graph-based linguistically motivated sentence representation and a typical neural network classifier applied to a task of recognition of CST relation in Polish. The representation describes selected levels of the sentence structure including description of lexical meanings on the basis of the wordnet (plWordNet) synsets and connected SUMO concepts. The obtained results show that in the case of difficult relations and medium size training corpus semantically enriched text representation leads to significantly better results.
dc.identifier.urihttp://hdl.handle.net/11321/981
dc.language.isoeng
dc.publisherGlobal Wordnet Association
dc.rightsCreative Commons - Attribution 4.0 International (CC BY 4.0)
dc.rights.labelCC
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectneural language models
dc.subjectCST relation
dc.titleNeural Language Models vs Wordnet-based Semantically Enriched Representation in CST Relation Recognition
dc.typelanguageDescription
local.contact.personAlicja Derych alicja.derych@pwr.edu.pl Politechnika Wrocławska
local.files.count1
local.files.size261821
local.has.filesyes
local.language.nameEnglish
metashare.ResourceInfo#ContentInfo.detailedTypeother
metashare.ResourceInfo#ContentInfo.mediaTypetext

Kolekcje

Language Descriptions
Ten zasób jestCCi został udostępniony na licencji:Creative Commons - Attribution 4.0 International (CC BY 4.0)
Attribution Required

Dostęp do plików

Pliki w tym zasobie

Pobierz kompletny pakiet albo skopiuj gotowe polecenie do automatycznego pobierania.

Nazwa
Jazn et al, Neural Language Models vs Wordnet-based Semantically Enriched Representation.pdf
Rozmiar
255.68 KB
Format
application/pdf
Opis
article
Suma kontrolna MD5
6d60186bd01b6ef55a21f881297d49aa
Preview
Podgląd pliku
  • Podgląd niedostępny

    Podgląd tego pliku nie został jeszcze wygenerowany. Spróbuj ponownie później albo skontaktuj się z administratorem systemu.

Uproszczony widok