We present a method for classifying syntactic errors in learner language, namely errors whose correction alters the morphosyntactic structure of a sentence. The methodology builds on the established Universal Dependencies syntactic representation scheme, and provides complementary information to other error-classification systems. Unlike existing error classification methods, our method is applicable across languages, which we showcase by producing a detailed picture of syntactic errors in learner English and learner Russian. We further demonstrate the utility of the methodology for analyzing the outputs of leading Grammatical Error Correction (GEC) systems.
|Original language||American English|
|Title of host publication||CoNLL 2020 - 24th Conference on Computational Natural Language Learning, Proceedings of the Conference|
|Editors||Raquel Fernandez, Tal Linzen|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||11|
|State||Published - 2020|
|Event||24th Conference on Computational Natural Language Learning, CoNLL 2020 - Virtual, Online|
Duration: 19 Nov 2020 → 20 Nov 2020
|Name||CoNLL 2020 - 24th Conference on Computational Natural Language Learning, Proceedings of the Conference|
|Conference||24th Conference on Computational Natural Language Learning, CoNLL 2020|
|Period||19/11/20 → 20/11/20|
Bibliographical noteFunding Information:
We thank Yarden Gavish for her help with coding and data preparation assignments. This work was supported by the Israel Science Foundation (grant no. 929/17). Leshem Choshen is supported
© 2020 Association for Computational Linguistics.