What does this research mean for the field?

Interval Bound Propagation can be utilized to achieve verified robustness against symbol substitutions in natural language processing models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 1, 2019Open Access

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation

View Full Paper

Ask AI

Bookmark

Abstract

Po-Sen Huang, Robert Stanforth, Johannes Welbl, Chris Dyer, Dani Yogatama, Sven Gowal, Krishnamurthy Dvijotham, Pushmeet Kohli. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Huang et al. (2019) studied this question.

synapsesocial.com/papers/6a0eef3653f874f2b222f862 https://doi.org/10.18653/v1/d19-1419

View Full Paper

Ask AI

Bookmark

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation

Abstract

Discussion

Cite This Study

Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation

Abstract

Discussion

Cite This Study

Keep reading

Keep reading