The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Combating Adversarial Misspellings with Robust Word Recognition
Open accessAbstract
To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier.Our word recognition models build upon the RNN semicharacter architecture, introducing several new backoff strategies for handling rare and unseen words.Trained to recognize words corrupted by random adds, drops, swaps, and keyboard mistakes, our method achieves 32% relative (and 3.3% absolute) error reduction over the vanilla semi-character model.Notably, our pipeline confers robustness on the downstream classifier, outperforming both adversarial training and off-the-shelf spell checkers.Against a BERT model fine-tuned for sentiment analysis, a single adversarially-chosen character attack lowers accuracy from 90.3% to 45.8%.Our defense restores accuracy to 75% 1 .Surprisingly, better word recognition does not always entail greater robustness.Our analysis reveals that robustness also depends upon a quantity that we denote the sensitivity.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
Learning Word Vectors for Sentiment Analysis
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011) · Cited by 6,961
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 1×
“Jia and Liang (2017) address the reading comprehension task, showing that by appending distractor sentences to the end of stories from the SQuAD dataset (Rajpurkar et al., 2016), they could cause models to output incorrect answers.”
BackgroundGoogle's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Xu, W., Evans, D., & Qi, Y. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23198 · Cited by 1,768
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410
Techniques for automatically correcting words in text
Kukich, K. (1992) · ACM Computing Surveys · doi:10.1145/146370.146380 · Cited by 1,257
Automatically Constructing a Corpus of Sentential Paraphrases.
Dolan, W. B., & Brockett, C. (2005) · Cited by 1,095
Thermometer Encoding: One Hot Way To Resist Adversarial Examples
Buckman, J., Roy, A., Raffel, C., & Goodfellow, I. (2018) · International Conference on Learning Representations · Cited by 702
The CoNLL-2014 Shared Task on Grammatical Error Correction
Ng, H. T., Wu, S. M., Briscoe, T., Hadiwinoto, C., Susanto, R. H., & Bryant, C. (2014) · Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task · doi:10.3115/v1/w14-1701 · Cited by 577
An improved error model for noisy channel spelling correction
Brill, E., & Moore, R. C. (2000) · Proceedings of the 38th Annual Meeting on Association for Computational Linguistics - ACL '00 · doi:10.3115/1075218.1075255 · Cited by 531
Generating Natural Adversarial Examples
Zhao, Z., Dua, D., & Singh, S. (2017) · arXiv · doi:10.48550/arxiv.1710.11342 · Cited by 508
Understanding Neural Networks through Representation Erasure
Li, J., Monroe, W., & Jurafsky, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08220 · Cited by 412
Synthetic and Natural Noise Both Break Neural Machine Translation
Belinkov, Y., & Bisk, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.02173 · Cited by 386
Breaking NLI Systems with Sentences that Require Simple Lexical Inferences
Glockner, M., Shwartz, V., & Goldberg, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2103 · Cited by 319
(2018) · International Conference on Learning Representations · Cited by 285
Context based spelling correction
Mays, E., Damerau, F. J., & Mercer, R. L. (1991) · Information Processing & Management · doi:10.1016/0306-4573(91)90066-u · Cited by 266
On Adversarial Examples for Character-Level Neural Machine TranslationPreprint
Ebrahimi, J., Lowd, D., & Dou, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.09030 · Cited by 222
Spam Filtering Based On The Analysis Of Text Information Embedded Into Images
Fumera, G., Pillai, I., & Roli, F. (2006) · UNICA IRIS Institutional Research Information System (University of Cagliari) · doi:10.5555/1248547.1248645 · Cited by 142
Robsut Wrod Reocginiton via Semi-Character Recurrent Neural Network
Sakaguchi, K., Duh, K., Post, M., & Durme, B. V. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10970 · Cited by 97
The Significance of Letter Position in Word Recognition
Rawlinson, G. (2007) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2007.327521 · Cited by 90
Sentence-Level Grammatical Error Identification as Sequence-to-Sequence Correction
Schmaltz, A., Kim, Y., Rush, A. M., & Shieber, S. M. (2016) · Workshop on Innovative Use of NLP for Building Educational Applications · doi:10.18653/v1/w16-0528 · Cited by 58
Spam deobfuscation using a hidden markov model
Lee, H., & Ng, A. Y. (2005) · Cited by 45
Spelling Error Correction Using a Nested RNN Model and Pseudo Training DataPreprint
Li, H., Wang, Y., Liu, X., Sheng, Z., & Wei, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.00238 · Cited by 32
Trends in transition from classical censorship to Internet censorship : selected country overviews
Bitso, C., Fourie, I., & Bothma, T. (2013) · UpSpace Institutional Repository (University of Pretoria) · Cited by 18
Cited by
BERT-ATTACK: Adversarial Attack Against BERT Using BERT
Li, L., Ma, R., Guo, Q., Xue, X., & Qiu, X. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.500 · Cited by 574
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP
Morris, J., Lifland, E., Yoo, J. Y., Grigsby, J., Jin, D., & Qi, Y. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.16 · Cited by 556
ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models
Xue, L., Barua, A., Constant, N., Al-Rfou, R., Narang, S., Kale, M., Roberts, A., & Raffel, C. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00461 · Cited by 330
AMMU: A survey of transformer-based biomedical pretrained language models
Kalyan, K. S., Rajasekharan, A., & Sangeetha, S. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103982 · Cited by 278
The Fallacy of AI Functionality
Raji, I. D., Kumar, I. E., Horowitz, A., & Selbst, A. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533158 · Cited by 251
Metadata
- Authors
- Pruthi, D., Dhingra, B., & Lipton, Z. C.
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 5582-5591
- OpenAlex
- W2947415936
- Cited by
- 275
- References
- 30
- FWCI
- 16.23
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.