The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Proceedings of the Conference)
Association for Computational Linguistics
Recurrent neural networks (RNNs) achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language. We investigate to what extent RNNs learn to track abstract hierarchical syntactic structure. We test whether RNNs trained with a generic language modeling objective in four languages (Italian, English, Hebrew, Russian) can predict long-distance number agreement in various constructions. We include in our evaluation nonsensical sentences where RNNs cannot rely on semantic or lexical cues (¿The colorless green ideas I ate with the chair sleep furiously¿), and, for Italian, we compare model performance to human intuitions. Our language-model-trained RNNs make reliable predictions about long-distance agreement, and do not lag much behind human performance. We thus bring support to the hypothesis that RNNs are not just shallow-pattern extractors, but they also acquire deeper grammatical competence.
Gulordava, K.; Bojanowski, P.; Grave, E.; Linzen, T.; Baroni, M.. Colorless green recurrent networks dream hierarchically. In: Walker, M.; Ji, H.; Stent, A. (eds.). The 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Proceedings of the Conference). 1 ed. East Stroudsburg PA: Association for Computational Linguistics; 2018. p. 1195-1205.