Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
The behavior of deep neural networks (DNNs) is hard to understand.This makes it necessary to explore post hoc explanation methods.We conduct the first comprehensive evaluation of explanation methods for NLP.To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems.Both paradigms require no manual annotation and are therefore broadly applicable.We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP.We show empirically that LIMSSE, LRP and DeepLIFT are the most effective explanation methods and recommend them for explaining DNNs in NLP.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 2×
“Gradient-based explanation methods approximate the contribution of some DNN input i to some output o with o ’s gradient with respect to i (Simonyan et al., 2014).”
BackgroundMethodOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 1×
“Goodman and Flaxman (2016)).”
Evaluating the Visualization of What a Deep Neural Network Has Learned
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., & Muller, K.-R. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2599820 · Cited by 1,164
Rationalizing Neural Predictions
Lei, T., Barzilay, R., & Jaakkola, T. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1011 · Cited by 777 · cited 2×
“, 2015) or rationale models (Lei et al., 2016)), as these are very specific architectures that may not be not applicable to all tasks.”
BackgroundVisualizing Deep Neural Network Decisions: Prediction Difference Analysis
Zintgraf, L. M., Cohen, T. S., Adel, T., & Welling, M. (2017) · arXiv · doi:10.48550/arxiv.1702.04595 · Cited by 487 · cited 1×
“In computer vision, perturbations are usually applied to patches, as neighboring pixels tend to correlate (Zintgraf et al., 2017).”
BackgroundExplaining Recurrent Neural Network Predictions in Sentiment Analysis
Arras, L., Montavon, G., Müller, K.-R., & Samek, W. (2017) · Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis · doi:10.18653/v1/w17-5221 · Cited by 361
Cited by
Layer-Wise Relevance Propagation: An Overview
Montavon, G., Binder, A., Lapuschkin, S., Samek, W., & Müller, K.-R. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-28954-6_10 · Cited by 750
Towards Explainable Artificial Intelligence
Samek, W., & Müller, K.-R. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-28954-6_1 · Cited by 580
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590
“"A good explanation method should not reflect what humans attend to, but what task methods attend to" [203].”
BackgroundRationales for Sequential Predictions
Vafa, K., Deng, Y., Blei, D., & Rush, A. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.807 · Cited by 14
Metadata
- Authors
- Poerner, N., Schütze, H., & Roth, B.
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2018
- Pages
- 340-350
- OpenAlex
- W2798698226
- Cited by
- 77
- References
- 10
- FWCI
- 5.62
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement. https://app.cochat.ai/papers/10.18653/v1/p18-1032
- The paper
- Poerner, N., Schütze, H., & Roth, B. (2018). Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/p18-1032
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.