We propose a novel approach to the study of how artificial neural network perceive the distinction between grammatical and ungrammatical sentences, a crucial task in the growing field of synthetic linguistics. The method is based on performance measures of language models trained on corpora and fine-tuned with either grammatical or ungrammatical sentences, then applied to (different types of) grammatical or ungrammatical sentences. The results show that both in the difficult and highly symmetrical task of detecting subject islands and in the more open CoLA dataset, grammatical sentences give rise to better scores than ungrammatical ones, possibly because they can be better integrated within the body of linguistic structural knowledge that the language model has accumulated.
An LSTM adaptation study of (Un)grammaticality / Chowdhury, Shammur Absar; Zamparelli, Roberto. - ELETTRONICO. - (2019), pp. 204-212. ((Intervento presentato al convegno BlackboxNLP tenutosi a Florence nel 1st August 2019.
|Titolo:||An LSTM adaptation study of (Un)grammaticality|
|Autori:||Chowdhury, Shammur Absar; Zamparelli, Roberto|
|Titolo del volume contenente il saggio:||Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP|
|Luogo di edizione:||Florence|
|Casa editrice:||Association for Computational Linguistics|
|Anno di pubblicazione:||2019|
|Citazione:||An LSTM adaptation study of (Un)grammaticality / Chowdhury, Shammur Absar; Zamparelli, Roberto. - ELETTRONICO. - (2019), pp. 204-212. ((Intervento presentato al convegno BlackboxNLP tenutosi a Florence nel 1st August 2019.|
|Appare nelle tipologie:||04.1 Saggio in atti di convegno (Paper in proceedings)|