---
title: "BlackboxNLP Workshop on Analyzing and Interpreting Neural"
description: "All 32 papers of BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2020, the most cited first; those with our…"
canonical: "https://research.elamur.ai/free/en/venues/blackboxnlp/2020/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/blackboxnlp/2020/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [BlackboxNLP Workshop on Analyzing and…](https://md.research.elamur.ai/free/en/venues/blackboxnlp/) / [2020](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2020/) / papers

# BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2020: all accepted papers

32 papers · the most cited first · [← BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2020](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2020/)

1. **[The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?](https://md.research.elamur.ai/free/en/papers/bastings-2020-elephant-interpretability-room-why-use/)**Jasmijn Bastings, Katja Filippova*150 citations · our summary*
2. **[What Happens To BERT Embeddings During Fine-tuning?](https://md.research.elamur.ai/free/en/papers/merchant-2020-what-happens-bert-embeddings-during/)**Amil Merchant, Elahe Rahimtoroghi, Ellie Pavlick et al.*139 citations · our summary*
3. **[BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance ↗](https://aclanthology.org/2020.blackboxnlp-1.21/)**R. Thomas McCoy, Junghyun Min, Tal Linzen*98 citations*
4. **[How does BERT capture semantics? A closer look at polysemous words ↗](https://aclanthology.org/2020.blackboxnlp-1.15/)**David Yenicelik, Florian Schmidt, Yannic Kilcher*50 citations*
5. **[Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation](https://md.research.elamur.ai/free/en/papers/geiger-2020-neural-natural-language-inference-models/)**Atticus Geiger, Kyle Richardson, Christopher Potts*44 citations · our summary*
6. **[Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples ↗](https://aclanthology.org/2020.blackboxnlp-1.30/)**Jin Yong Yoo, John Morris, Eli Lifland et al.*43 citations*
7. **[It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT ↗](https://aclanthology.org/2020.blackboxnlp-1.5/)**Hila Gonen, Shauli Ravfogel, Yanai Elazar et al.*40 citations*
8. **[BERTnesia: Investigating the capture and forgetting of knowledge in BERT ↗](https://aclanthology.org/2020.blackboxnlp-1.17/)**Jonas Wallat, Jaspreet Singh, Avishek Anand*30 citations*
9. **[Discovering the Compositional Structure of Vector Representations with Role Learning Networks ↗](https://aclanthology.org/2020.blackboxnlp-1.23/)**Paul Soulos, R. Thomas McCoy, Tal Linzen et al.*26 citations*
10. **[Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets ↗](https://aclanthology.org/2020.blackboxnlp-1.12/)**Chuanrong Li, Lin Shengshuo, Zeyu Liu et al.*25 citations*
11. **[The Explanation Game: Towards Prediction Explainability through Sparse Communication ↗](https://aclanthology.org/2020.blackboxnlp-1.10/)**Marcos Treviso, André F. T. Martins*25 citations*
12. **[Do Language Embeddings capture Scales? ↗](https://aclanthology.org/2020.blackboxnlp-1.27/)**Xikun Zhang, Deepak Ramachandran, Ian Tenney et al.*22 citations*
13. **[The EOS Decision and Length Extrapolation ↗](https://aclanthology.org/2020.blackboxnlp-1.26/)**Benjamin Newman, John Hewitt, Percy Liang et al.*22 citations*
14. **[On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers ↗](https://aclanthology.org/2020.blackboxnlp-1.7/)**Marius Mosbach, Anna Khokhlova, Michael A. Hedderich et al.*17 citations*
15. **[Emergent Language Generalization and Acquisition Speed are not tied to Compositionality ↗](https://aclanthology.org/2020.blackboxnlp-1.2/)**Eugene Kharitonov, Marco Baroni*16 citations*
16. **[Structured Self-Attention Weights Encode Semantics in Sentiment Analysis ↗](https://aclanthology.org/2020.blackboxnlp-1.24/)**Zhengxuan Wu, Thanh-Son Nguyen, Desmond C. Ong*16 citations*
17. **[Investigating Novel Verb Learning in BERT: Selectional Preference Classes and Alternation-Based Syntactic Generalization ↗](https://aclanthology.org/2020.blackboxnlp-1.25/)**Tristan Thrush, Ethan Wilcox, Roger Levy*13 citations*
18. **[Probing for Multilingual Numerical Understanding in Transformer-Based Language Models ↗](https://aclanthology.org/2020.blackboxnlp-1.18/)**Devin Johnson, Denise Mak, Andrew Barker et al.*13 citations*
19. **[This is a BERT. Now there are several of them. Can they generalize to novel words? ↗](https://aclanthology.org/2020.blackboxnlp-1.31/)**Coleman Haley*11 citations*
20. **[Defining Explanation in an AI Context ↗](https://aclanthology.org/2020.blackboxnlp-1.29/)**Tejaswani Verma, Christoph Lingenfelder, Dietrich Klakow*9 citations*
21. **[Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation ↗](https://aclanthology.org/2020.blackboxnlp-1.19/)**Rajiv Movva, Jason Zhao*9 citations*
22. **[Examining the rhetorical capacities of neural language models ↗](https://aclanthology.org/2020.blackboxnlp-1.3/)**Zining Zhu, Chuer Pan, Mohamed Abdalla et al.*8 citations*
23. **[Unsupervised Distillation of Syntactic Information from Contextualized Word Representations ↗](https://aclanthology.org/2020.blackboxnlp-1.9/)**Shauli Ravfogel, Yanai Elazar, Jacob Goldberger et al.*8 citations*
24. **[Evaluating Attribution Methods using White-Box LSTMs ↗](https://aclanthology.org/2020.blackboxnlp-1.28/)**Yiding Hao*7 citations*
25. **[diagNNose: A Library for Neural Activation Analysis ↗](https://aclanthology.org/2020.blackboxnlp-1.32/)**Jaap Jumelet*7 citations*
26. **[Exploring Neural Entity Representations for Semantic Information ↗](https://aclanthology.org/2020.blackboxnlp-1.20/)**Andrew Runge, Eduard Hovy*5 citations*
27. **[Unsupervised Evaluation for Question Answering with Transformers ↗](https://aclanthology.org/2020.blackboxnlp-1.8/)**Lukas Muttenthaler, Isabelle Augenstein, Johannes Bjerva*4 citations*
28. **[Controlling the Imprint of Passivization and Negation in Contextualized Representations ↗](https://aclanthology.org/2020.blackboxnlp-1.13/)**Hande Celikkanat, Sami Virpioja, Jörg Tiedemann et al.*3 citations*
29. **[BERTering RAMS: What and How Much does BERT Already Know About Event Arguments? - A Study on the RAMS Dataset ↗](https://aclanthology.org/2020.blackboxnlp-1.1/)**Varun Gangal, Eduard Hovy*2 citations*
30. **[Latent Tree Learning with Ordered Neurons: What Parses Does It Produce? ↗](https://aclanthology.org/2020.blackboxnlp-1.11/)**Yian Zhang*1 citation*
31. **[Second-Order NLP Adversarial Examples ↗](https://aclanthology.org/2020.blackboxnlp-1.22/)**John Morris*1 citation*
32. **[Leveraging Extracted Model Adversaries for Improved Black Box Attacks ↗](https://aclanthology.org/2020.blackboxnlp-1.6/)**Naveen Jafer Nizar, Ari Kobren
- [← back to](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2020/) — BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2020