Neural Network Acceptability Judgments
Abstrak
Abstract This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence, with the goal of testing their linguistic competence. We introduce the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature. As baselines, we train several recurrent neural network models on acceptability classification, and find that our models outperform unsupervised models by Lau et al. (2016) on CoLA. Error-analysis on specific grammatical phenomena reveals that both Lau et al.’s models and ours learn systematic generalizations like subject-verb-object order. However, all models we test perform far below human level on a wide range of grammatical constructions.
Topik & Kata Kunci
Penulis (3)
Alex Warstadt
Amanpreet Singh
Samuel R. Bowman
Akses Cepat
- Tahun Terbit
- 2018
- Bahasa
- en
- Total Sitasi
- 1592×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1162/tacl_a_00290
- Akses
- Open Access ✓