The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra argu- ments and subject-relative clause island violations), and considers its implications for the de- bate on language innatism. The results show that the current RNN model can correctly classify (un)grammatical sentences, in certain conditions, but it is sensitive to linguistic processing fac- tors and probably ultimately unable to induce a more abstract notion of grammaticality, at least in the domain we tested.

RNN Simulations of Grammaticality Judgments on Long-distance Dependencies / Chowdhury, Shammur Absar; Zamparelli, Roberto. - ELETTRONICO. - (2018), pp. 133-144.

RNN Simulations of Grammaticality Judgments on Long-distance Dependencies

Chowdhury, Shammur Absar;Zamparelli, Roberto
2018

Abstract

The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra argu- ments and subject-relative clause island violations), and considers its implications for the de- bate on language innatism. The results show that the current RNN model can correctly classify (un)grammatical sentences, in certain conditions, but it is sensitive to linguistic processing fac- tors and probably ultimately unable to induce a more abstract notion of grammaticality, at least in the domain we tested.
Proceedings of the 27th International Conference on Computational Linguistics: COLING
Santa Fa, NM, USA
ICCL
978-1-948087-50-6
Chowdhury, Shammur Absar; Zamparelli, Roberto
RNN Simulations of Grammaticality Judgments on Long-distance Dependencies / Chowdhury, Shammur Absar; Zamparelli, Roberto. - ELETTRONICO. - (2018), pp. 133-144.
File in questo prodotto:
File Dimensione Formato  
chowdhury-zamparelli-coling2018.pdf

accesso aperto

Descrizione: Articolo principale da atti del convegno
Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 445.16 kB
Formato Adobe PDF
445.16 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/222409
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact