The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Semantically Equivalent Adversarial Rules for Debugging NLP models
Open accessAbstract
Complex machine learning models for NLP are often brittle, making different predictions for input instances that are extremely similar semantically. To automatically detect this behavior for individual instances, we present semantically equivalent adversaries (SEAs) – semantic-preserving perturbations that induce changes in the model’s predictions. We generalize these adversaries into semantically equivalent adversarial rules (SEARs) – simple, universal replacement rules that induce adversaries on many instances. We demonstrate the usefulness and flexibility of SEAs and SEARs by detecting bugs in black-box state-of-the-art models for three domains: machine comprehension, visual question-answering, and sentiment analysis. Via user studies, we demonstrate that we generate high-quality local adversaries for more instances than humans, and that SEARs induce four times as many mistakes as the bugs discovered by human experts. SEARs are also actionable: retraining models using data augmentation significantly reduces bugs, while maintaining accuracy.
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
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Self-citationIntriguing 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
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 2×
“With increasing complexity of models for tasks like classification (Joulin et al., 2016), machine comprehension (Rajpurkar et al., 2016; Seo et al., 2017), and visual question answering (Zhu et al., 2016), models are becoming increasingly challenging to debug, and to determine whether they are…”
BackgroundDistributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 1×
“Previous work on debugging primarily focuses on explaining predictions in validation data in order to uncover bugs (Ribeiro et al., 2016, 2018; Kulesza et al., 2011), or find labeling errors (Zhang et al., 2018; Koh and Liang, 2017).”
BackgroundSelf-citationPang, B., & Lee, L. (2005) · Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05 · doi:10.3115/1219840.1219855 · Cited by 2,129
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Klein, G., Kim, Y., Deng, Y., Senellart, J., & Rush, A. (2017) · Proceedings of ACL 2017, System Demonstrations · doi:10.18653/v1/p17-4012 · Cited by 1,749
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514
Bidirectional Attention Flow for Machine Comprehension
Seo, M. J., Kembhavi, A., Farhadi, A., & Hajishirzi, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01603 · Cited by 1,445
Parallel Data, Tools and Interfaces in OPUS
Tiedemann, J. (2012) · Language Resources and Evaluation · Cited by 1,421
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
AllenNLP: A Deep Semantic Natural Language Processing Platform
Gardner, M., Grus, J., Neumann, M., Tafjord, O., Dasigi, P., Liu, N. F., Peters, M., Schmitz, M., & Zettlemoyer, L. (2018) · Proceedings of Workshop for NLP Open Source Software (NLP-OSS) · doi:10.18653/v1/w18-2501 · Cited by 1,252
Visual7W: Grounded Question Answering in Images
Zhu, Y., Groth, O., Bernstein, M., & Fei-Fei, L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.540 · Cited by 794 · cited 4×
“, 2017), and visual question answering (Zhu et al., 2016), models are becoming increasingly challenging to debug, and to determine whether they are ready for deployment.”
BackgroundMethodInfluentialSubmodular Function Maximization
Krause, A., & Golovin, D. (2014) · Tractability · doi:10.1017/cbo9781139177801.004 · Cited by 751
Pang, B., & Lee, L. (2005) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0506075 · Cited by 678
Adversarial Example Generation with Syntactically Controlled Paraphrase Networks
Iyyer, M., Wieting, J., Gimpel, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1170 · Cited by 615
Generating Natural Adversarial Examples
Zhao, Z., Dua, D., & Singh, S. (2017) · arXiv · doi:10.48550/arxiv.1710.11342 · Cited by 508 · cited 7×
“Other paraphrase limitations: Paraphrase models based on neural machine translation are biased towards maintaining the sentence structure, and thus do not produce certain adversaries (e.g. Table 5b), which recent work on paraphrasing (Iyyer et al., 2018) or generation using GANs (Zhao et al., 2018) may address.”
BackgroundSelf-citationUnderstanding Neural Networks through Representation Erasure
Li, J., Monroe, W., & Jurafsky, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08220 · Cited by 412
From Group to Individual Labels Using Deep Features
Kotzias, D., Denil, M., de Freitas, N., & Smyth, P. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783380 · Cited by 312
Paraphrasing Revisited with Neural Machine Translation
Mallinson, J., Sennrich, R., & Lapata, M. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers · doi:10.18653/v1/e17-1083 · Cited by 206
Investigating statistical machine learning as a tool for software development
Patel, K., Fogarty, J. A., Landay, J. A., & Harrison, B. L. (2008) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/1357054.1357160 · Cited by 136
Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings
Wieting, J., & Gimpel, K. (2017) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p17-1190 · Cited by 88
Training Set Debugging Using Trusted Items
Zhang, X., Zhu, X., & Wright, S. J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11610 · Cited by 79
Why-oriented end-user debugging of naive Bayes text classification
Kulesza, T., Stumpf, S., Wong, W., Burnett, M., Perona, S., Ko, A. J., & Oberst, I. (2011) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/2030365.2030367 · Cited by 69
Towards Transparent Systems: Semantic Characterization of Failure Modes
Bansal, A., Farhadi, A., & Parikh, D. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10599-4_24 · Cited by 34
Cited by
BLEURT: Learning Robust Metrics for Text Generation
Sellam, T., Das, D., & Parikh, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.704 · Cited by 1,005
BLEURT: Learning Robust Metrics for Text Generation
Sellam, T., Das, D., & Parikh, A. P. (2020) · arXiv · doi:10.48550/arxiv.2004.04696 · Cited by 1,005
A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective
Roh, Y., Heo, G., & Whang, S. E. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2946162 · Cited by 968
Jin, D., Jin, Z., Zhou, J. T., & Szolovits, P. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6311 · Cited by 918
Beyond accuracy: behavioral testing of NLP models with CheckList
Ribeiro, M. T., Wu, T., Guestrin, C., & Singh, S. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.442 · Cited by 890
Self-citation
Metadata
- Authors
- Ribeiro, M. T., Singh, S., & Guestrin, C.
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2018
- Pages
- 856-865
- OpenAlex
- W2799007037
- Cited by
- 432
- References
- 27
- FWCI
- 28.40
- 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.