---
title: "A Survey of the State of Explainable AI — Danilevsky 2020"
description: "Modern NLP has moved from transparent methods such as rules, decision trees and HMMs to deep neural models and embeddings."
authors: ["Marina Danilevsky", "Kun Qian", "Ranit Aharonov", "Yannis Katsis", "Ban Kawas", "Prithviraj Sen"]
year: 2020
venue: "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing"
source: "https://aclanthology.org/2020.aacl-main.46/"
doi: "10.18653/v1/2020.aacl-main.46"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/danilevsky-2020-survey-state-explainable-ai-natural/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/danilevsky-2020-survey-state-explainable-ai-natural/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/page/2/) / A Survey of the State of Explainable AI for Natural Language Processing

# A Survey of the State of Explainable AI for Natural Language Processing

**Authors:** [Marina Danilevsky](https://md.research.elamur.ai/free/en/authors/marina-danilevsky/), Kun Qian, Ranit Aharonov, [Yannis Katsis](https://md.research.elamur.ai/free/en/authors/yannis-katsis/), Ban Kawas, Prithviraj Sen · **Year:** 2020 · **Venue:** Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.aacl-main.46/) · [PDF](https://aclanthology.org/2020.aacl-main.46.pdf) · [DOI 10.18653/v1/2020.aacl-main.46](https://doi.org/10.18653/v1/2020.aacl-main.46) · [OpenAlex](https://openalex.org/W3117696238)

**Citations:** 203 citations (openalex-snapshot · 2026-10-14) · [87](https://md.research.elamur.ai/free/en/papers/danilevsky-2020-survey-state-explainable-ai-natural/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Modern NLP has moved from transparent methods such as rules, decision trees and HMMs to deep neural models and embeddings. These are more accurate but much harder to interpret, which can undermine user trust. The authors present what they describe as the first survey of Explainable AI (XAI) devoted specifically to NLP. It covers 50 papers from major NLP venues over roughly seven years, and each paper was classified by at least two reviewers. Papers are organised along two established axes: whether an explanation is local or global, and whether it is self-explaining or post-hoc. The survey adds further dimensions: the technique used to derive the explanation, the underlying operations (such as attention or input perturbation), and how the explanation is shown to users. It also reviews evaluation practice and introduces predictive process coverage, meaning how much of the input-to-output reasoning an explanation actually exposes. The main conclusion is that the field lacks formal definitions, standardised evaluation and attention to fidelity. This matters for developers who want to choose suitable explainability methods.

## Key points
- Of the 50 surveyed papers, 46 offer local explanations and only 4 offer global ones. The authors see the neglect of white box models as a missed testbed for evaluating explanations.
- Five major explainability techniques are identified, among them feature importance, surrogate models (e.g. LIME), example-driven methods and provenance-based methods.
- Attention and first-derivative saliency are the most common operations behind feature-importance explanations. Surrogate models raise concerns about fidelity.
- The MathQA examples (Amini et al., 2019 vs Ling et al., 2017) show that explanations differ in how much of the prediction process they cover.
- An interactive companion website is available at https://xainlp2020.github.io/xainlp/. The survey proposes three future directions:
  - clearer terminology tied to the target audience;
  - better human-centred evaluation metrics;
  - closer scrutiny of faithfulness.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{danilevsky2020survey,
  title = {{A Survey of the State of Explainable AI for Natural Language Processing}},
  author = {Danilevsky, Marina and Qian, Kun and Aharonov, Ranit and Katsis, Yannis and Kawas, Ban and Sen, Prithviraj},
  booktitle = {Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing},
  year = {2020},
  doi = {10.18653/v1/2020.aacl-main.46},
  url = {https://doi.org/10.18653/v1/2020.aacl-main.46}
}
```

- [← previous SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://md.research.elamur.ai/free/en/papers/jiang-2020-smart-robust-efficient-fine-tuning/)
- [next → CAMeL Tools: An Open Source Python Toolkit for Arabic Natural Language Processing](https://md.research.elamur.ai/free/en/papers/obeid-2020-camel-tools-open-source-python/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/page/2/)

## References

71 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, and Gerhard Weikum. 2017. Quint: Interpretable question answering over knowledge bases. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 61–66. [find](https://scholar.google.com/scholar?q=Abdalghani+Abujabal%2C+Rishiraj+Saha+Roy%2C+Mohamed+Yahya%2C+and+Gerhard+Weikum%2E+2017%2E+Quint%3A+Interpretable+question+answering+over+knowledge+bases%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Method)
2. A. Adadi and M. Berrada. 2018. Peeking inside the black-box: A survey on explainable artificial intelligence (xai). IEEE Access, 6:52138–52160. [find](https://scholar.google.com/scholar?q=A%2E+Adadi+and+M%2E+Berrada%2E+2018%2E+Peeking+inside+the+black%2Dbox%3A+A+survey+on+explainable+artificial+intelligence+%28xai%29%2E+IEEE+Access%2C+6%3A52138%E2%80%9352160%2E)
3. Zakaria Aldeneh and Emily Mower Provost. 2017. Using regional saliency for speech emotion recognition. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2741–2745. IEEE. [find](https://scholar.google.com/scholar?q=Zakaria+Aldeneh+and+Emily+Mower+Provost%2E+2017%2E+Using+regional+saliency+for+speech+emotion+recognition%2E+In+2017+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29%2C+pages+)
4. David Alvarez-Melis and Tommi Jaakkola. 2017. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 412– 421, Copenhagen, Denmark. Association for Computational Ling… [find](https://scholar.google.com/scholar?q=David+Alvarez%2DMelis+and+Tommi+Jaakkola%2E+2017%2E+A+causal+framework+for+explaining+the+predictions+of+black%2Dbox+sequence%2Dto%2Dsequence+models%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+)
5. Aida Amini, Saadia Gabriel, Shanchuan Lin, Rik Koncel-Kedziorski, Yejin Choi, and Hannaneh Hajishirzi. 2019. MathQA: Towards interpretable math word problem solving with operation-based formalisms. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computation… [find](https://scholar.google.com/scholar?q=Aida+Amini%2C+Saadia+Gabriel%2C+Shanchuan+Lin%2C+Rik+Koncel%2DKedziorski%2C+Yejin+Choi%2C+and+Hannaneh+Hajishirzi%2E+2019%2E+MathQA%3A+Towards+interpretable+math+word+problem+solving+with+operation%2Dbased+formalisms%2E+In) [our card](https://md.research.elamur.ai/free/en/papers/amini-2019-mathqa-interpretable-math-word-problem/)
6. Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John T. Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Var… — [arXiv:1909.03012](https://arxiv.org/abs/1909.03012) [find](https://scholar.google.com/scholar?q=Vijay+Arya%2C+Rachel+K%2E+E%2E+Bellamy%2C+Pin%2DYu+Chen%2C+Amit+Dhurandhar%2C+Michael+Hind%2C+Samuel+C%2E+Hoffman%2C+Stephanie+Houde%2C+Q%2E+Vera+Liao%2C+Ronny+Luss%2C+Aleksandra+Mojsilovic%2C+Sami+Mourad%2C+Pablo+Pedemonte%2C+Ramya+R)
7. M. Aubakirova and M. Bansal. 2016. Interpreting neural networks to improve politeness comprehension. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (Austin, Texas, 2016), page 2035–2041. [find](https://scholar.google.com/scholar?q=M%2E+Aubakirova+and+M%2E+Bansal%2E+2016%2E+Interpreting+neural+networks+to+improve+politeness+comprehension%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28Austin%2C+) [our card](https://md.research.elamur.ai/free/en/papers/aubakirova-2016-interpreting-neural-networks-improve-politeness/)
8. AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2018. Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume… [find](https://scholar.google.com/scholar?q=AmirAli+Bagher+Zadeh%2C+Paul+Pu+Liang%2C+Soujanya+Poria%2C+Erik+Cambria%2C+and+Louis%2DPhilippe+Morency%2E+2018%2E+Multimodal+language+analysis+in+the+wild%3A+CMU%2DMOSEI+dataset+and+interpretable+dynamic+fusion+graph%2E) [our card](https://md.research.elamur.ai/free/en/papers/zadeh-2018-multimodal-language-analysis-wild-cmu/)
9. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In ICLR. [find](https://scholar.google.com/scholar?q=Dzmitry+Bahdanau%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+2015%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+In+ICLR%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
10. Francesco Barbieri, Luis Espinosa-Anke, Jose Camacho-Collados, Steven Schockaert, and Horacio Saggion. 2018. Interpretable emoji prediction via label-wise attention LSTMs. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4766–4771, Brussels, Belgium. A… [find](https://scholar.google.com/scholar?q=Francesco+Barbieri%2C+Luis+Espinosa%2DAnke%2C+Jose+Camacho%2DCollados%2C+Steven+Schockaert%2C+and+Horacio+Saggion%2E+2018%2E+Interpretable+emoji+prediction+via+label%2Dwise+attention+LSTMs%2E+In+Proceedings+of+the+2018+C)
11. Dimitris Bertsimas, Arthur Delarue, Patrick Jaillet, and Sébastien Martin. 2019. The price of interpretability. ArXiv, abs/1907.03419. — [arXiv:1907.03419](https://arxiv.org/abs/1907.03419) [find](https://scholar.google.com/scholar?q=Dimitris+Bertsimas%2C+Arthur+Delarue%2C+Patrick+Jaillet%2C+and+Se%CC%81bastien+Martin%2E+2019%2E+The+price+of+interpretability%2E+ArXiv%2C+abs%2F1907%2E03419%2E+%E2%80%94+%5BarXiv%3A1907%2E03419%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1907%2E03419%29)
12. Nikita Bhutani, Kun Qian, Yunyao Li, H. V. Jagadish, Mauricio Hernandez, and Mitesh Vasa. 2018. Exploiting structure in representation of named entities using active learning. In Proceedings of the 27th International Conference on Computational Linguistics, pages 687–699, Santa Fe, New Mexico, USA.… [find](https://scholar.google.com/scholar?q=Nikita+Bhutani%2C+Kun+Qian%2C+Yunyao+Li%2C+H%2E+V%2E+Jagadish%2C+Mauricio+Hernandez%2C+and+Mitesh+Vasa%2E+2018%2E+Exploiting+structure+in+representation+of+named+entities+using+active+learning%2E+In+Proceedings+of+the+27)
13. Samuel Carton, Qiaozhu Mei, and Paul Resnick. 2018. Extractive adversarial networks: High-recall explanations for identifying personal attacks in social media posts. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3497–3507, Brussels, Belgium. Associa… [find](https://scholar.google.com/scholar?q=Samuel+Carton%2C+Qiaozhu+Mei%2C+and+Paul+Resnick%2E+2018%2E+Extractive+adversarial+networks%3A+High%2Drecall+explanations+for+identifying+personal+attacks+in+social+media+posts%2E+In+Proceedings+of+the+2018+Confere)
14. Diogo V. Carvalho, Eduardo M. Pereira, and Jaime S. Cardoso. 2019. Machine Learning Interpretability: A Survey on Methods and Metrics. Electronics, 8(8):832. Number: 8 Publisher: Multidisciplinary Digital Publishing Institute. [find](https://scholar.google.com/scholar?q=Diogo+V%2E+Carvalho%2C+Eduardo+M%2E+Pereira%2C+and+Jaime+S%2E+Cardoso%2E+2019%2E+Machine+Learning+Interpretability%3A+A+Survey+on+Methods+and+Metrics%2E+Electronics%2C+8%288%29%3A832%2E+Number%3A+8+Publisher%3A+Multidisciplinary+Dig)
15. Danilo Croce, Daniele Rossini, and Roberto Basili. 2018. Explaining non-linear classifier decisions within kernel-based deep architectures. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 16–24, Brussels, Belgium. Association for Compu… [find](https://scholar.google.com/scholar?q=Danilo+Croce%2C+Daniele+Rossini%2C+and+Roberto+Basili%2E+2018%2E+Explaining+non%2Dlinear+classifier+decisions+within+kernel%2Dbased+deep+architectures%2E+In+Proceedings+of+the+2018+EMNLP+Workshop+BlackboxNLP%3A+Analy)
16. Danilo Croce, Daniele Rossini, and Roberto Basili. 2019. Auditing deep learning processes through kernel-based explanatory models. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNL… [find](https://scholar.google.com/scholar?q=Danilo+Croce%2C+Daniele+Rossini%2C+and+Roberto+Basili%2E+2019%2E+Auditing+deep+learning+processes+through+kernel%2Dbased+explanatory+models%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural)
17. Yue Dong, Zichao Li, Mehdi Rezagholizadeh, and Jackie Chi Kit Cheung. 2019. EditNTS: An neural programmer-interpreter model for sentence simplification through explicit editing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3393–3402, Florence, Ita… [find](https://scholar.google.com/scholar?q=Yue+Dong%2C+Zichao+Li%2C+Mehdi+Rezagholizadeh%2C+and+Jackie+Chi+Kit+Cheung%2E+2019%2E+EditNTS%3A+An+neural+programmer%2Dinterpreter+model+for+sentence+simplification+through+explicit+editing%2E+In+Proceedings+of+the+) [our card](https://md.research.elamur.ai/free/en/papers/dong-2019-editnts-neural-programmer-interpreter-model/)
18. Sahibsingh A Dudani. 1976. The distance-weighted k-nearest-neighbor rule. IEEE Transactions on Systems, Man, and Cybernetics, (4):325–327. [find](https://scholar.google.com/scholar?q=Sahibsingh+A+Dudani%2E+1976%2E+The+distance%2Dweighted+k%2Dnearest%2Dneighbor+rule%2E+IEEE+Transactions+on+Systems%2C+Man%2C+and+Cybernetics%2C+%284%29%3A325%E2%80%93327%2E)
19. Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez, and Jordan Boyd-Graber. 2018. Pathologies of neural models make interpretations difficult. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3719–3728, Brussels, Belgium. Associatio… [find](https://scholar.google.com/scholar?q=Shi+Feng%2C+Eric+Wallace%2C+Alvin+Grissom+II%2C+Mohit+Iyyer%2C+Pedro+Rodriguez%2C+and+Jordan+Boyd%2DGraber%2E+2018%2E+Pathologies+of+neural+models+make+interpretations+difficult%2E+In+Proceedings+of+the+2018+Conference)
20. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, , and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. JMLR. [find](https://scholar.google.com/scholar?q=Yaroslav+Ganin%2C+Evgeniya+Ustinova%2C+Hana+Ajakan%2C+Pascal+Germain%2C+Hugo+Larochelle%2C+Franc%CC%A7ois+Laviolette%2C+Mario+Marchand%2C+%2C+and+Victor+Lempitsky%2E+2016%2E+Domain%2Dadversarial+training+of+neural+networks%2E+JML)
21. Nicolas Garneau, Jean-Samuel Leboeuf, and Luc Lamontagne. 2018. Predicting and interpreting embeddings for out of vocabulary words in downstream tasks. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 331–333, Brussels, Belgium. Associa… [find](https://scholar.google.com/scholar?q=Nicolas+Garneau%2C+Jean%2DSamuel+Leboeuf%2C+and+Luc+Lamontagne%2E+2018%2E+Predicting+and+interpreting+embeddings+for+out+of+vocabulary+words+in+downstream+tasks%2E+In+Proceedings+of+the+2018+EMNLP+Workshop+Blackb)
22. Reza Ghaeini, Xiaoli Fern, and Prasad Tadepalli. 2018. Interpreting recurrent and attention-based neural models: a case study on natural language inference. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4952–4957, Brussels, Belgium. Association for… [find](https://scholar.google.com/scholar?q=Reza+Ghaeini%2C+Xiaoli+Fern%2C+and+Prasad+Tadepalli%2E+2018%2E+Interpreting+recurrent+and+attention%2Dbased+neural+models%3A+a+case+study+on+natural+language+inference%2E+In+Proceedings+of+the+2018+Conference+on+Em)
23. Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, and Thomas Demeester. 2018. Explaining character-aware neural networks for word-level prediction: Do they discover linguistic rules? In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3275– 328… [find](https://scholar.google.com/scholar?q=Fre%CC%81deric+Godin%2C+Kris+Demuynck%2C+Joni+Dambre%2C+Wesley+De+Neve%2C+and+Thomas+Demeester%2E+2018%2E+Explaining+character%2Daware+neural+networks+for+word%2Dlevel+prediction%3A+Do+they+discover+linguistic+rules%3F+In+Pro)
24. Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pedreschi. 2018. A survey of methods for explaining black box models. ACM Comput. Surv., 51(5). [find](https://scholar.google.com/scholar?q=Riccardo+Guidotti%2C+Anna+Monreale%2C+Salvatore+Ruggieri%2C+Franco+Turini%2C+Fosca+Giannotti%2C+and+Dino+Pedreschi%2E+2018%2E+A+survey+of+methods+for+explaining+black+box+models%2E+ACM+Comput%2E+Surv%2E%2C+51%285%29%2E)
25. Pankaj Gupta and Hinrich Schütze. 2018. LISA: Explaining recurrent neural network judgments via layer-wIse semantic accumulation and example to pattern transformation. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 154–164, Brussels,… [find](https://scholar.google.com/scholar?q=Pankaj+Gupta+and+Hinrich+Schu%CC%88tze%2E+2018%2E+LISA%3A+Explaining+recurrent+neural+network+judgments+via+layer%2DwIse+semantic+accumulation+and+example+to+pattern+transformation%2E+In+Proceedings+of+the+2018+EMNL)
26. Joseph Y. Halpern. 2016. Actual Causality. MIT Press. [find](https://scholar.google.com/scholar?q=Joseph+Y%2E+Halpern%2E+2016%2E+Actual+Causality%2E+MIT+Press%2E)
27. David Harbecke, Robert Schwarzenberg, and Christoph Alt. 2018. Learning explanations from language data. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 316–318, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=David+Harbecke%2C+Robert+Schwarzenberg%2C+and+Christoph+Alt%2E+2018%2E+Learning+explanations+from+language+data%2E+In+Proceedings+of+the+2018+EMNLP+Workshop+BlackboxNLP%3A+Analyzing+and+Interpreting+Neural+Networ)
28. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+Computation%2E)
29. Shiou Tian Hsu, Changsung Moon, Paul Jones, and Nagiza Samatova. 2018. An interpretable generative adversarial approach to classification of latent entity relations in unstructured sentences. In AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Shiou+Tian+Hsu%2C+Changsung+Moon%2C+Paul+Jones%2C+and+Nagiza+Samatova%2E+2018%2E+An+interpretable+generative+adversarial+approach+to+classification+of+latent+entity+relations+in+unstructured+sentences%2E+In+AAAI+)
30. Sarthak Jain and Byron C. Wallace. 2019. Attention is not Explanation. In 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), pages 3543–3556, Minneapolis, Minnesota. Associa… [find](https://scholar.google.com/scholar?q=Sarthak+Jain+and+Byron+C%2E+Wallace%2E+2019%2E+Attention+is+not+Explanation%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational+Linguistics%3A+Human+Langu) [our card](https://md.research.elamur.ai/free/en/papers/jain-2019-attention-is-not-explanation/)
31. Yichen Jiang and Mohit Bansal. 2019. Self-assembling modular networks for interpretable multi-hop reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4474–… [find](https://scholar.google.com/scholar?q=Yichen+Jiang+and+Mohit+Bansal%2E+2019%2E+Self%2Dassembling+modular+networks+for+interpretable+multi%2Dhop+reasoning%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing+a)
32. Yichen Jiang, Nitish Joshi, Yen-Chun Chen, and Mohit Bansal. 2019. Explore, propose, and assemble: An interpretable model for multi-hop reading comprehension. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2714–2725, Florence, Italy. Association for… [find](https://scholar.google.com/scholar?q=Yichen+Jiang%2C+Nitish+Joshi%2C+Yen%2DChun+Chen%2C+and+Mohit+Bansal%2E+2019%2E+Explore%2C+propose%2C+and+assemble%3A+An+interpretable+model+for+multi%2Dhop+reading+comprehension%2E+In+Proceedings+of+the+57th+Annual+Meeting)
33. Dongyeop Kang, Varun Gangal, Ang Lu, Zheng Chen, and Eduard Hovy. 2017. Detecting and explaining causes from text for a time series event. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2758– 2767, Copenhagen, Denmark. Association for Computational L… [find](https://scholar.google.com/scholar?q=Dongyeop+Kang%2C+Varun+Gangal%2C+Ang+Lu%2C+Zheng+Chen%2C+and+Eduard+Hovy%2E+2017%2E+Detecting+and+explaining+causes+from+text+for+a+time+series+event%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in)
34. Sweta Karlekar, Tong Niu, and Mohit Bansal. 2018. Detecting linguistic characteristics of alzheimer’s dementia by interpreting neural models. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (S… [find](https://scholar.google.com/scholar?q=Sweta+Karlekar%2C+Tong+Niu%2C+and+Mohit+Bansal%2E+2018%2E+Detecting+linguistic+characteristics+of+alzheimer%E2%80%99s+dementia+by+interpreting+neural+models%2E+In+Proceedings+of+the+2018+Conference+of+the+North+America)
35. Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, and Masaaki Nagata. 2018. Unsupervised token-wise alignment to improve interpretation of encoder-decoder models. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 74–81,… [find](https://scholar.google.com/scholar?q=Shun+Kiyono%2C+Sho+Takase%2C+Jun+Suzuki%2C+Naoaki+Okazaki%2C+Kentaro+Inui%2C+and+Masaaki+Nagata%2E+2018%2E+Unsupervised+token%2Dwise+alignment+to+improve+interpretation+of+encoder%2Ddecoder+models%2E+In+Proceedings+of+th)
36. Freddy Lecue, Krishna Gade, Sahin Cem Geyik, Krishnaram Kenthapadi, Varun Mithal, Ankur Taly, Riccardo Guidotti, and Pasquale Minervini. 2020. Explainable ai: Foundations, industrial applications, practical challenges, and lessons learned. In AAAI Conference on Artificial Intelligence. Association f… [find](https://scholar.google.com/scholar?q=Freddy+Lecue%2C+Krishna+Gade%2C+Sahin+Cem+Geyik%2C+Krishnaram+Kenthapadi%2C+Varun+Mithal%2C+Ankur+Taly%2C+Riccardo+Guidotti%2C+and+Pasquale+Minervini%2E+2020%2E+Explainable+ai%3A+Foundations%2C+industrial+applications%2C+pra)
37. Piyawat Lertvittayakumjorn and Francesca Toni. 2019. Human-grounded evaluations of explanation methods for text classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-I… [find](https://scholar.google.com/scholar?q=Piyawat+Lertvittayakumjorn+and+Francesca+Toni%2E+2019%2E+Human%2Dgrounded+evaluations+of+explanation+methods+for+text+classification%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+La)
38. Jiwei Li, Xinlei Chen, Eduard Hovy, and Dan Jurafsky. 2015. Visualizing and understanding neural models in nlp. arXiv preprint arXiv:1506.01066. [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Xinlei+Chen%2C+Eduard+Hovy%2C+and+Dan+Jurafsky%2E+2015%2E+Visualizing+and+understanding+neural+models+in+nlp%2E+arXiv+preprint+arXiv%3A1506%2E01066%2E) [our card](https://md.research.elamur.ai/free/en/papers/li-2016-visualizing-understanding-neural-models-nlp/)
39. Qiuchi Li, Benyou Wang, and Massimo Melucci. 2019. CNM: An interpretable complex-valued network for matching. In 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), pages 413… [find](https://scholar.google.com/scholar?q=Qiuchi+Li%2C+Benyou+Wang%2C+and+Massimo+Melucci%2E+2019%2E+CNM%3A+An+interpretable+complex%2Dvalued+network+for+matching%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapter+of+the+Association+for)
40. Chao-Chun Liang, Shih-Hong Tsai, Ting-Yun Chang, Yi-Chung Lin, and Keh-Yih Su. 2016. A meaning-based English math word problem solver with understanding, reasoning and explanation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations, p… [find](https://scholar.google.com/scholar?q=Chao%2DChun+Liang%2C+Shih%2DHong+Tsai%2C+Ting%2DYun+Chang%2C+Yi%2DChung+Lin%2C+and+Keh%2DYih+Su%2E+2016%2E+A+meaning%2Dbased+English+math+word+problem+solver+with+understanding%2C+reasoning+and+explanation%2E+In+Proceedings+of+C)
41. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
42. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. 2017. Program induction by rationale generation: Learning to solve and explain algebraic word problems. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 158–167, Vancouver… [find](https://scholar.google.com/scholar?q=Wang+Ling%2C+Dani+Yogatama%2C+Chris+Dyer%2C+and+Phil+Blunsom%2E+2017%2E+Program+induction+by+rationale+generation%3A+Learning+to+solve+and+explain+algebraic+word+problems%2E+In+Proceedings+of+the+55th+Annual+Meetin)
43. Hui Liu, Qingyu Yin, and William Yang Wang. 2019. Towards explainable NLP: A generative explanation framework for text classification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5570–5581, Florence, Italy. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Hui+Liu%2C+Qingyu+Yin%2C+and+William+Yang+Wang%2E+2019%2E+Towards+explainable+NLP%3A+A+generative+explanation+framework+for+text+classification%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+)
44. Ninghao Liu, Xiao Huang, Jundong Li, and Xia Hu. 2018. On interpretation of network embedding via taxonomy induction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’18, page 1812–1820, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Ninghao+Liu%2C+Xiao+Huang%2C+Jundong+Li%2C+and+Xia+Hu%2E+2018%2E+On+interpretation+of+network+embedding+via+taxonomy+induction%2E+In+Proceedings+of+the+24th+ACM+SIGKDD+International+Conference+on+Knowledge+Discov)
45. Junyu Lu, Chenbin Zhang, Zeying Xie, Guang Ling, Tom Chao Zhou, and Zenglin Xu. 2019. Constructing interpretive spatio-temporal features for multi-turn responses selection. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 44–50, Florence, Italy. Assoc… [find](https://scholar.google.com/scholar?q=Junyu+Lu%2C+Chenbin+Zhang%2C+Zeying+Xie%2C+Guang+Ling%2C+Tom+Chao+Zhou%2C+and+Zenglin+Xu%2E+2019%2E+Constructing+interpretive+spatio%2Dtemporal+features+for+multi%2Dturn+responses+selection%2E+In+Proceedings+of+the+57th+)
46. Ling Luo, Xiang Ao, Feiyang Pan, Jin Wang, Tong Zhao, Ningzi Yu, and Qing He. 2018. Beyond polarity: Interpretable financial sentiment analysis with hierarchical query-driven attention. [find](https://scholar.google.com/scholar?q=Ling+Luo%2C+Xiang+Ao%2C+Feiyang+Pan%2C+Jin+Wang%2C+Tong+Zhao%2C+Ningzi+Yu%2C+and+Qing+He%2E+2018%2E+Beyond+polarity%3A+Interpretable+financial+sentiment+analysis+with+hierarchical+query%2Ddriven+attention%2E)
47. Seungwhan Moon, Pararth Shah, Anuj Kumar, and Rajen Subba. 2019. OpenDialKG: Explainable conversational reasoning with attention-based walks over knowledge graphs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 845–854, Florence, Italy. Association… [find](https://scholar.google.com/scholar?q=Seungwhan+Moon%2C+Pararth+Shah%2C+Anuj+Kumar%2C+and+Rajen+Subba%2E+2019%2E+OpenDialKG%3A+Explainable+conversational+reasoning+with+attention%2Dbased+walks+over+knowledge+graphs%2E+In+Proceedings+of+the+57th+Annual+Me) [our card](https://md.research.elamur.ai/free/en/papers/moon-2019-opendialkg-explainable-conversational-reasoning-attention/)
48. James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, and Jacob Eisenstein. 2018. Explainable prediction of medical codes from clinical text. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1… [find](https://scholar.google.com/scholar?q=James+Mullenbach%2C+Sarah+Wiegreffe%2C+Jon+Duke%2C+Jimeng+Sun%2C+and+Jacob+Eisenstein%2E+2018%2E+Explainable+prediction+of+medical+codes+from+clinical+text%2E+In+Proceedings+of+the+2018+Conference+of+the+North+Amer) [our card](https://md.research.elamur.ai/free/en/papers/mullenbach-2018-explainable-prediction-medical-codes-clinical/)
49. An Nguyen, Aditya Kharosekar, Matthew Lease, and Byron Wallace. 2018. An interpretable joint graphical model for fact-checking from crowds. In AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=An+Nguyen%2C+Aditya+Kharosekar%2C+Matthew+Lease%2C+and+Byron+Wallace%2E+2018%2E+An+interpretable+joint+graphical+model+for+fact%2Dchecking+from+crowds%2E+In+AAAI+Conference+on+Artificial+Intelligence%2E)
50. Alexander Panchenko, Fide Marten, Eugen Ruppert, Stefano Faralli, Dmitry Ustalov, Simone Paolo Ponzetto, and Chris Biemann. 2017. Unsupervised, knowledge-free, and interpretable word sense disambiguation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: Syst… [find](https://scholar.google.com/scholar?q=Alexander+Panchenko%2C+Fide+Marten%2C+Eugen+Ruppert%2C+Stefano+Faralli%2C+Dmitry+Ustalov%2C+Simone+Paolo+Ponzetto%2C+and+Chris+Biemann%2E+2017%2E+Unsupervised%2C+knowledge%2Dfree%2C+and+interpretable+word+sense+disambiguat)
51. Nikolaos Pappas and Andrei Popescu-Belis. 2014. Explaining the stars: Weighted multiple-instance learning for aspect-based sentiment analysis. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 455–466, Doha, Qatar. Association for Computational… [find](https://scholar.google.com/scholar?q=Nikolaos+Pappas+and+Andrei+Popescu%2DBelis%2E+2014%2E+Explaining+the+stars%3A+Weighted+multiple%2Dinstance+learning+for+aspect%2Dbased+sentiment+analysis%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Method)
52. Pouya Pezeshkpour, Yifan Tian, and Sameer Singh. 2019a. Investigating robustness and interpretability of link prediction via adversarial modifications. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, V… [find](https://scholar.google.com/scholar?q=Pouya+Pezeshkpour%2C+Yifan+Tian%2C+and+Sameer+Singh%2E+2019a%2E+Investigating+robustness+and+interpretability+of+link+prediction+via+adversarial+modifications%2E+In+Proceedings+of+the+2019+Conference+of+the+Nor)
53. Pouya Pezeshkpour, Yifan Tian, and Sameer Singh. 2019b. Investigating robustness and interpretability of link prediction via adversarial modifications. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, V… [find](https://scholar.google.com/scholar?q=Pouya+Pezeshkpour%2C+Yifan+Tian%2C+and+Sameer+Singh%2E+2019b%2E+Investigating+robustness+and+interpretability+of+link+prediction+via+adversarial+modifications%2E+In+Proceedings+of+the+2019+Conference+of+the+Nor)
54. Nina Poerner, Hinrich Schütze, and Benjamin Roth. 2018. Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 340–350, Melbourne, A… [find](https://scholar.google.com/scholar?q=Nina+Poerner%2C+Hinrich+Schu%CC%88tze%2C+and+Benjamin+Roth%2E+2018%2E+Evaluating+neural+network+explanation+methods+using+hybrid+documents+and+morphosyntactic+agreement%2E+In+Proceedings+of+the+56th+Annual+Meeting+o)
55. Nicolas Pröllochs, Stefan Feuerriegel, and Dirk Neumann. 2019. Learning interpretable negation rules via weak supervision at document level: A reinforcement learning approach. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human… [find](https://scholar.google.com/scholar?q=Nicolas+Pro%CC%88llochs%2C+Stefan+Feuerriegel%2C+and+Dirk+Neumann%2E+2019%2E+Learning+interpretable+negation+rules+via+weak+supervision+at+document+level%3A+A+reinforcement+learning+approach%2E+In+Proceedings+of+the+2)
56. Reid Pryzant, Sugato Basu, and Kazoo Sone. 2018a. Interpretable neural architectures for attributing an ad’s performance to its writing style. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 125–135, Brussels, Belgium. Association for… [find](https://scholar.google.com/scholar?q=Reid+Pryzant%2C+Sugato+Basu%2C+and+Kazoo+Sone%2E+2018a%2E+Interpretable+neural+architectures+for+attributing+an+ad%E2%80%99s+performance+to+its+writing+style%2E+In+Proceedings+of+the+2018+EMNLP+Workshop+BlackboxNLP%3A+An)
57. Reid Pryzant, Kelly Shen, Dan Jurafsky, and Stefan Wagner. 2018b. Deconfounded lexicon induction for interpretable social science. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)… [find](https://scholar.google.com/scholar?q=Reid+Pryzant%2C+Kelly+Shen%2C+Dan+Jurafsky%2C+and+Stefan+Wagner%2E+2018b%2E+Deconfounded+lexicon+induction+for+interpretable+social+science%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+o)
58. Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, and Richard Socher. 2019a. Explain yourself! leveraging language models for commonsense reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4932–4942, Florence, Italy. Association for Computa… [find](https://scholar.google.com/scholar?q=Nazneen+Fatema+Rajani%2C+Bryan+McCann%2C+Caiming+Xiong%2C+and+Richard+Socher%2E+2019a%2E+Explain+yourself%21+leveraging+language+models+for+commonsense+reasoning%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+) [our card](https://md.research.elamur.ai/free/en/papers/rajani-2019-explain-yourself-leveraging-language-models/)
59. Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, and Richard Socher. 2019b. Explain yourself! leveraging language models for commonsense reasoning. arXiv preprint arXiv:1906.02361. [find](https://scholar.google.com/scholar?q=Nazneen+Fatema+Rajani%2C+Bryan+McCann%2C+Caiming+Xiong%2C+and+Richard+Socher%2E+2019b%2E+Explain+yourself%21+leveraging+language+models+for+commonsense+reasoning%2E+arXiv+preprint+arXiv%3A1906%2E02361%2E) [our card](https://md.research.elamur.ai/free/en/papers/rajani-2019-explain-yourself-leveraging-language-models/)
60. Ehud Reiter and Robert Dale. 1997. Building applied natural language generation systems. Natural Language Engineering, 3(1):57–87. [find](https://scholar.google.com/scholar?q=Ehud+Reiter+and+Robert+Dale%2E+1997%2E+Building+applied+natural+language+generation+systems%2E+Natural+Language+Engineering%2C+3%281%29%3A57%E2%80%9387%2E)
61. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?”: Explaining the predictions of any classifier. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (New York, NY, USA, 2016), page 1135–1144. [find](https://scholar.google.com/scholar?q=Marco+Tulio+Ribeiro%2C+Sameer+Singh%2C+and+Carlos+Guestrin%2E+2016%2E+Why+should+i+trust+you%3F%E2%80%9D%3A+Explaining+the+predictions+of+any+classifier%2E+In+Proceedings+of+the+22Nd+ACM+SIGKDD+International+Conference+on+) [our card](https://md.research.elamur.ai/free/en/papers/ribeiro-2016-why-should-i-trust-explaining/)
62. Andrew Slavin Ross, Michael C. Hughes, and Finale Doshi-Velez. 2017. Right for the right reasons: Training differentiable models by constraining their explanations. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pages 2662–2670. [find](https://scholar.google.com/scholar?q=Andrew+Slavin+Ross%2C+Michael+C%2E+Hughes%2C+and+Finale+Doshi%2DVelez%2E+2017%2E+Right+for+the+right+reasons%3A+Training+differentiable+models+by+constraining+their+explanations%2E+In+Proceedings+of+the+Twenty%2DSixth+)
63. A. Saltelli, M. Ratto, T. Andres, F. Campolongo, J. Cariboni, D. Gatelli, M. Saisana, and S. Tarantola. 2008. Global Sensitivity Analysis: The Primer. John Wiley & Sons. [find](https://scholar.google.com/scholar?q=A%2E+Saltelli%2C+M%2E+Ratto%2C+T%2E+Andres%2C+F%2E+Campolongo%2C+J%2E+Cariboni%2C+D%2E+Gatelli%2C+M%2E+Saisana%2C+and+S%2E+Tarantola%2E+2008%2E+Global+Sensitivity+Analysis%3A+The+Primer%2E+John+Wiley+%26+Sons%2E)
64. Robert Schwarzenberg, David Harbecke, Vivien Macketanz, Eleftherios Avramidis, and Sebastian Möller. 2019. Train, sort, explain: Learning to diagnose translation models. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrati… [find](https://scholar.google.com/scholar?q=Robert+Schwarzenberg%2C+David+Harbecke%2C+Vivien+Macketanz%2C+Eleftherios+Avramidis%2C+and+Sebastian+Mo%CC%88ller%2E+2019%2E+Train%2C+sort%2C+explain%3A+Learning+to+diagnose+translation+models%2E+In+Proceedings+of+the+2019+Co)
65. Prithviraj Sen, Yunyao Li, Eser Kandogan, Yiwei Yang, and Walter Lasecki. 2019. HEIDL: Learning linguistic expressions with deep learning and human-in-the-loop. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 135–140, Florence,… [find](https://scholar.google.com/scholar?q=Prithviraj+Sen%2C+Yunyao+Li%2C+Eser+Kandogan%2C+Yiwei+Yang%2C+and+Walter+Lasecki%2E+2019%2E+HEIDL%3A+Learning+linguistic+expressions+with+deep+learning+and+human%2Din%2Dthe%2Dloop%2E+In+Proceedings+of+the+57th+Annual+Meeti)
66. Sofia Serrano and Noah A. Smith. 2019. Is attention interpretable? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2931–2951, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sofia+Serrano+and+Noah+A%2E+Smith%2E+2019%2E+Is+attention+interpretable%3F+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+2931%E2%80%932951%2C+Florence%2C+Italy%2E+Associa) [our card](https://md.research.elamur.ai/free/en/papers/serrano-2019-is-attention-interpretable/)
67. Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034. [find](https://scholar.google.com/scholar?q=Karen+Simonyan%2C+Andrea+Vedaldi%2C+and+Andrew+Zisserman%2E+2013%2E+Deep+inside+convolutional+networks%3A+Visualising+image+classification+models+and+saliency+maps%2E+arXiv+preprint+arXiv%3A1312%2E6034%2E) [our card](https://md.research.elamur.ai/free/en/papers/simonyan-2013-deep-inside-convolutional-networks-visualising/)
68. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International Conference on Machine Learning, Sydney, Australia. [find](https://scholar.google.com/scholar?q=Mukund+Sundararajan%2C+Ankur+Taly%2C+and+Qiqi+Yan%2E+2017%2E+Axiomatic+attribution+for+deep+networks%2E+In+International+Conference+on+Machine+Learning%2C+Sydney%2C+Australia%2E)
69. Alona Sydorova, Nina Poerner, and Benjamin Roth. 2019. Interpretable question answering on knowledge bases and text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4943–4951, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alona+Sydorova%2C+Nina+Poerner%2C+and+Benjamin+Roth%2E+2019%2E+Interpretable+question+answering+on+knowledge+bases+and+text%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Ling)
70. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2019. Generating token-level explanations for natural language inference. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, V… [find](https://scholar.google.com/scholar?q=James+Thorne%2C+Andreas+Vlachos%2C+Christos+Christodoulopoulos%2C+and+Arpit+Mittal%2E+2019%2E+Generating+token%2Dlevel+explanations+for+natural+language+inference%2E+In+Proceedings+of+the+2019+Conference+of+the+Nor)
71. Martin Tutek and Jan Šnajder. 2018. Iterative recursive attention model for interpretable sequence classification. In Proceedings of the 2018 EMNLP Work- [find](https://scholar.google.com/scholar?q=Martin+Tutek+and+Jan+S%CC%8Cnajder%2E+2018%2E+Iterative+recursive+attention+model+for+interpretable+sequence+classification%2E+In+Proceedings+of+the+2018+EMNLP+Work%2D)