Judging Grammaticality: Experiments in Sentence Classification
By Joachim Wagner, Jennifer Foster, Josef van Genabith. 2013
50 citations recorded by the source corpus.
A classifier which is capable of distinguishing a syntactically well formed sentence from a syntactically ill formed one has the potential to be useful in an L2 language-learning context. In this article, we describe a classifier which classifies English sentences as either well formed or ill formed using information gleaned from three different natural language processing techniques. We describe the issues involved in acquiring data to train such a classifier and present experimental results for this classifier on a variety of ill formed sentences. We demonstrate that (a) the combination of information from a variety of linguistic sources is helpful, (b) the trade-off between accuracy on well formed sentences and accuracy on ill formed sentences can be fine tuned by training multiple classifiers in a voting scheme, and (c) the performance of the classifier is varied, with better performance on transcribed spoken sentences produced by less advanced language learners.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Samuel R. Bowman
- Alex Warstadt
- Jackie Chi Kit Cheung
- Mohit Bansal
- Iacer Calixto
- Chris Hokamp
- Yejin Choi
- Gerald Penn
Citations in the corpus
- Target-Centric Features for Translation Quality Estimation (2014, methodology): “These features have been shown to be useful for judging the grammaticality of sentences (Wagner et al., 2009; Wagner, 2012) and have been used in MT quality estimation before (Rubino et al., 2012; Rubino et al., 2013).”
- Grammatical Analysis of Pretrained Sentence Encoders with Acceptability Judgments (2019, background): “Wagner et al. (2009) Joachim Wagner, Jennifer Foster, and Josef van Genabith.”
- Unsupervised Sentence Enhancement for Automatic Summarization (2014, background): “Parse log likelihoods have been shown to be useful in determining grammaticality (Wagner et al., 2009), and many of the problems associated with using it do not apply in our evaluation, because our sentences have a fixed number of content nodes, and contain similar content.”