What do RNN Language Models Learn about Filler-Gap Dependencies?

Ethan Wilcox, Roger Levy, Takashi Morita, Richard Futrell. What do RNN Language Models Learn about Filler-Gap Dependencies?. In Tal Linzen, Grzegorz Chrupala, Afra Alishahi, editors, Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2018, Brussels, Belgium, November 1, 2018. pages 211-221, Association for Computational Linguistics, 2018. [doi]

@inproceedings{WilcoxLMF18,
  title = {What do RNN Language Models Learn about Filler-Gap Dependencies?},
  author = {Ethan Wilcox and Roger Levy and Takashi Morita and Richard Futrell},
  year = {2018},
  url = {https://aclanthology.info/papers/W18-5423/w18-5423},
  researchr = {https://researchr.org/publication/WilcoxLMF18},
  cites = {0},
  citedby = {0},
  pages = {211-221},
  booktitle = {Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2018, Brussels, Belgium, November 1, 2018},
  editor = {Tal Linzen and Grzegorz Chrupala and Afra Alishahi},
  publisher = {Association for Computational Linguistics},
  isbn = {978-1-948087-71-1},
}