dm.cs.tu-dortmund.de/en/mlbits/neural-nlp-limitations/
Discussion of Neural NLP – Lecture Notes
R., Bowman, S.R. and Smith, N.A. 2018. Annotation artifacts in natural language inference data. NAACL-HLT (2018), 107–112.
[KaLi18]
Kaushik, D. and Lipton, Z.C. 2018. How much reading does reading co [...] V. and Goldberg, Y. 2018. Breaking NLI systems with sentences that require simple lexical inferences. Proc. 56th ann. Meeting association for computational linguistics, ACL (2018), 650–655.
[GSLS18]
[...] approaches tend to show human-like biases [ BCZS16 ; CaBrNa17 ] that may be difficult to fix:
2015:
2018:
https://www.technologyreview.com/the-download/609959/google-photos-still-has-a-problem-with-gorillas/ …
