Work

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

Year: 2018
Type: paratext
Abstract: We received an impressive number of 76 submissions (including both archival papers and extended abstracts), suggesting that the issue of interpretability of neural networks is timely and important within the NLP community.The final program contains three keynote talks, eight oral presentations and 47 posters.We hope this workshop provides a venue for bringing together ideas and stimulate new ways of building methods and resources for facilitating better analysis and understanding of the inner-dynamics of neural networks for NLP.BlackboxNLP would not have been possible without the dedication of its program committee.We would like to thank them for their invaluable effort in providing high-quality reviews in a very short period of time and for a higher number of submission originally expected.We are also grateful to our invited speakers,
Language: English
Open Access status: gold
OpenAlex ID: W2971031791
Cites: 576
Cited by: 130
Related to: 10