Proceedings of the 2018 EMNLP Workshop BlackboxNLP : Analyzing and Interpreting Neural Networks for NLP

98 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Compositionality Decomposed: How do Neural Networks Generalise? (2019, background): “…it means to say that a model is or is not compositional, a point exempliﬁed by the vast number of different tests that exist for compositionality [ Lake and Baroni, 2018; Hupkes et al. , 2018; Johnson et al. , 2017; Bahdanau et al. , 2018; Saxton et al. , 2019; Loula et al. , 2018; Dess`ı and…”
Positional Artefacts Propagate Through Masked Language Model Embeddings (2020, background): “Indeed, an entire research area central to this core issue — the interpretability of neural NLP models — has recently emerged (Linzen et al., 2018, 2019; Alishahi et al., 2020).”
Pareto Probing: Trading-Off Accuracy and Complexity (2020, background): “This lack of understanding, coupled with the rising adoption of neural NLP systems in both industry and academia, has fomented a rapidly growing literature devoted to “cracking open the black box”, as it were (Alishahi et al., 2019; Linzen et al., 2019).”
LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations (2019, background): “Despite their impressive performance, interpreting, analyzing and evaluating such black-box models have been shown to be challenging, which even led to a set of workshop series (Linzen et al., 2018).”