Comparing Automatic and Human Evaluation of Local Explanations for Text Classification
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Text classification models are becoming increasingly complex and opaque, however for many applications it is essential that the models are interpretable.Recently, a variety of approaches have been proposed for generating local explanations.While robust evaluations are needed to drive further progress, so far it is unclear which evaluation approaches are suitable.This paper is a first step towards more robust evaluations of local explanations.We evaluate a variety of local explanation approaches using automatic measures based on word deletion.Furthermore, we show that an evaluation using a crowdsourcing experiment correlates moderately with these automatic measures and that a variety of other factors also impact the human judgements.
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., 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
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 2×
“Various approaches have been explored to increase the interpretability of machine learning models (Lipton, 2016).”
BackgroundDeep 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 3×
“Research on interpretable machine learning models has so far mainly focused on computer vision systems (e.g., Simonyan et al. (2013)).”
BackgroundTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Explaining collaborative filtering recommendations
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000) · Proceedings of the 2000 ACM conference on Computer supported cooperative work · doi:10.1145/358916.358995 · Cited by 1,731 · cited 1×
“A study by Herlocker et al. (2000) found that providing local explanations could help improve the acceptance of movie recommendation systems.”
BackgroundUnderstanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 3×
“Expanding the explanation with for example influential documents (Koh and Liang, 2017) or a visualization of the class distributions of the most influential words could make the explanations more informative.”
BackgroundInfluentialEvaluating 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
Principles of Explanatory Debugging to Personalize Interactive Machine Learning
Kulesza, T., Burnett, M., Wong, W.-K., & Stumpf, S. (2015) · Proceedings of the 20th International Conference on Intelligent User Interfaces · doi:10.1145/2678025.2701399 · Cited by 576
Why and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552 · cited 1×
“For some models the local explanations are relatively easy to construct, e.g., displaying the word probabilities of a Naive Bayes model with respect to each label (Kulesza et al., 2015) or displaying the path of a decision tree (Lim et al., 2009).”
BackgroundExplaining Data-Driven Document Classifications1
Martens, D., & Provost, F. (2014) · MIS Quarterly · doi:10.25300/misq/2014/38.1.04 · Cited by 264 · cited 4×
“…and Bansal, 2016; Li et al., 2016a; Simonyan et al., 2013), measuring the effect of removing individual words (or features) (Li et al., 2016b; Martens and Provost, 2014), decomposition approaches (Arras et al., 2016; Ding et al., 2017), and training an interpretable classifier (e.g., linear…”
BackgroundMethodInfluential
Cited by
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. S. (2020) · arXiv · doi:10.48550/arxiv.2006.14779 · Cited by 754
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Bansal, G., Wu, T., Zhou, J., Fok, R., Nushi, B., Kamar, E., Ribeiro, M. T., & Weld, D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445717 · Cited by 757
“red no specific background knowledge. We chose text classification because it is a popular task in natural language processing (NLP) that has been used in several previous studies on human-AI teaming [17, 24, 35, 43, 53, 70], requires little domain expertise, and is thus amenable to crowdsourcing.Further, there are va…”
MethodSerrano, S., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1282 · Cited by 690
“Nguyen (2018) leveraged the idea of minimal sets in a much more similar way to our work, comparing different input importance orderings.”
ResultTowards 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
ERASER: A Benchmark to Evaluate Rationalized NLP Models
DeYoung, J., Jain, S., Rajani, N. F., Lehman, E., Xiong, C., Socher, R., & Wallace, B. C. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.408 · Cited by 561
Metadata
- Authors
- Nguyen, D.
- Venue
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
- Published
- 2018
- Pages
- 1069-1078
- OpenAlex
- W2804878416
- Cited by
- 173
- References
- 10
- FWCI
- 7.70
- 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.