AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Open accessAbstract
Eric Wallace, Jens Tuyls, Junlin Wang, Sanjay Subramanian, Matt Gardner, Sameer Singh. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations. 2019.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Gradient-based interpretability methods have been shown to be useful in computer vision and NLP.
“Gradient-based interpretability methods have been shown to be useful in computer vision and NLP (Sundararajan et al., 2017; Wallace et al., 2019).”
From AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders (2025) · cites this paper as Wallace et al., 2019
Despite attempts such as analyzing internal attention weights or employing interpretation tools and visualization techniques, word-level explanations are insufficient.
“Despite attempts such as analyzing internal attention weights or employing interpretation tools and visualization techniques [Wallace et al., 2019], word-level explanations are insufficient.”
From Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges (2025) · cites this paper as Wallace et al., 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 28 · Cited by 116
Research works printed but not linked: 19
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Ben- gio. 2015. Neural machine translation by jointly learning to align and translate. In ICLR.
- Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou. 2018. HotFlip: White-box adversarial exam- ples for text classification. In ACL.
- Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, and Jordan Boyd-Graber. 2018. Pathologies of neural models make interpretations difficult. In EMNLP.
- Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Pe- ters, Michael Schmitz, and Luke Zettlemoyer. 2018. AllenNLP: A deep semantic natural language pro- cessing platform. In ACL Workshop for NLP Open Source Software.
- Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel R. Bowman, and Noah A. Smith. 2018. Annotation artifacts in natural lan- guage inference data. In NAACL.
- Andrej Karpathy, Justin Johnson, and Li Fei-Fei. 2016. Visualizing and understanding recurrent networks. In ICLR Workshop Track.
- Gyeongbok Lee, Sungdong Kim, and Seung-won Hwang. 2019. QADiver: Interactive framework for diagnosing QA models. In AAAI Demonstrations.
- Shusen Liu, Tao Li, Zhimin Li, Vivek Srikumar, Vale- rio Pascucci, and Peer-Timo Bremer. 2018. Visual interrogation of attention-based models for natural language inference and machine comprehension. In EMNLP.
- Andrew P Norton and Yanjun Qi. 2017. Adversarial- Playground: A visualization suite showing how ad- versarial examples fool deep learning. In 2017 IEEE VizSec Symposium.
- Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Ku- rakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, et al. 2016. Technical report on the CleverHans v2.1.0 adversarial examples library. arXiv:1610.00768. · arXiv
- Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. In NAACL.
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In EMNLP.
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should I trust you?: Explain- ing the predictions of any classifier. In KDD.
- Min Joon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2017. Bidirectional attention flow for machine comprehension. In ICLR.
- Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda B. Viégas, and Martin Wattenberg. 2017. SmoothGrad: removing noise by adding noise. In ICML Workshop on Visualization for Deep Learning.
- Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister, and Alexander M Rush. 2019. Seq2Seq-Vis: A visual debugging tool for sequence-to-sequence models. IEEE TVCG.
- Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In ICML.
- Jesse Vig. 2019. Visualizing attention in transformer- based language models. arXiv:1904.02679. · arXiv
- Eric Wallace, Shi Feng, and Jordan Boyd-Graber. 2018. Interpreting neural networks with nearest neighbors. In EMNLP 2018 Blackbox NLP Workshop.
- Authors
- Wallace, E., Tuyls, J., Wang, J., Subramanian, S., Gardner, M., & Singh, S.
- Affiliations
- Allen Institute for Artificial Intelligence (US)
- University of California, Irvine (US)
- Venue
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations
- Published
- 2019
- Pages
- 7-12
- OpenAlex
- W2970863760
- Cited by
- 116
- References
- 28
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 12 · 2023: 18 · 2022: 27 · 2021: 30 · 2020: 23 · 2019: 1
- FWCI
- 7.75
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) (publishedVersion, cc-by)
- Funders
- National Science Foundation (1756023)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- interpretability, natural language processing models
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
