Neural Network Acceptability Judgments
This work addresses the challenge of assessing linguistic competence in AI models for researchers in computational linguistics, though it is incremental as it builds on existing methods with new data.
The paper tackles the problem of evaluating neural networks' ability to judge grammatical acceptability, using the introduced Corpus of Linguistic Acceptability (CoLA) with 10,657 labeled sentences, and finds that their models outperform unsupervised baselines but still perform far below human level.
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.