---
title: "EMNLP Workshop BlackboxNLP: Analyzing and Interpreting"
description: "All 56 papers of EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP 2018, the most cited first; those with…"
canonical: "https://research.elamur.ai/free/en/venues/emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp/2018/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp/2018/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [EMNLP Workshop BlackboxNLP: Analyzing…](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp/) / [2018](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp/2018/) / papers

# EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP 2018: all accepted papers

56 papers · the most cited first · [← EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP 2018](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp/2018/)

1. **[GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://md.research.elamur.ai/free/en/papers/wang-2018-glue-multi-task-benchmark-analysis/)**Alex Wang, Amanpreet Singh, Julian Michael et al.*4,074 citations · our summary*
2. **[An Analysis of Encoder Representations in Transformer-Based Machine Translation](https://md.research.elamur.ai/free/en/papers/raganato-2018-analysis-encoder-representations-transformer-based/)**Alessandro Raganato, Jörg Tiedemann*265 citations · our summary*
3. **[Understanding Convolutional Neural Networks for Text Classification ↗](https://aclanthology.org/W18-5408/)**Alon Jacovi, Oren Sar Shalom, Yoav Goldberg*226 citations*
4. **[On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis ↗](https://aclanthology.org/W18-5406/)**Jose Camacho-Collados, Mohammad Taher Pilehvar*164 citations*
5. **[What do RNN Language Models Learn about Filler–Gap Dependencies?](https://md.research.elamur.ai/free/en/papers/wilcox-2018-rnn-language-models-learn-about/)**Ethan Wilcox, Roger Levy, Takashi Morita et al.*154 citations · our summary*
6. **[Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis ↗](https://aclanthology.org/W18-5448/)**Kelly Zhang, Samuel R. Bowman*112 citations*
7. **[Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks](https://md.research.elamur.ai/free/en/papers/loula-2018-rearranging-familiar-testing-compositional-generalization/)**João Loula, Marco Baroni, Brenden Lake*106 citations · our summary*
8. **[Importance of Self-Attention for Sentiment Analysis ↗](https://aclanthology.org/W18-5429/)**Gaël Letarte, Frédérik Paradis, Philippe Giguère et al.*67 citations*
9. **[Interpreting Neural Networks with Nearest Neighbors ↗](https://aclanthology.org/W18-5416/)**Eric Wallace, Shi Feng, Jordan Boyd-Graber*64 citations*
10. **[Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items ↗](https://aclanthology.org/W18-5424/)**Jaap Jumelet, Dieuwke Hupkes*61 citations*
11. **[Evaluating the Ability of LSTMs to Learn Context-Free Grammars ↗](https://aclanthology.org/W18-5414/)**Luzi Sennhauser, Robert Berwick*51 citations*
12. **[An Operation Sequence Model for Explainable Neural Machine Translation ↗](https://aclanthology.org/W18-5420/)**Felix Stahlberg, Danielle Saunders, Bill Byrne*47 citations*
13. **[Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation ↗](https://aclanthology.org/W18-5441/)**Adam Poliak, Aparajita Haldar, Rachel Rudinger et al.*42 citations*
14. **[Can LSTM Learn to Capture Agreement? The Case of Basque ↗](https://aclanthology.org/W18-5412/)**Shauli Ravfogel, Yoav Goldberg, Francis Tyers*38 citations*
15. **[Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell ↗](https://aclanthology.org/W18-5430/)**Pia Sommerauer, Antske Fokkens*33 citations*
16. **[Does Syntactic Knowledge in Multilingual Language Models Transfer Across Languages? ↗](https://aclanthology.org/W18-5453/)**Prajit Dhar, Arianna Bisazza*31 citations*
17. **[Extracting Syntactic Trees from Transformer Encoder Self-Attentions ↗](https://aclanthology.org/W18-5444/)**David Mareček, Rudolf Rosa*31 citations*
18. **[Context-Free Transductions with Neural Stacks ↗](https://aclanthology.org/W18-5433/)**Yiding Hao, William Merrill, Dana Angluin et al.*25 citations*
19. **[Closing Brackets with Recurrent Neural Networks ↗](https://aclanthology.org/W18-5425/)**Natalia Skachkova, Thomas Trost, Dietrich Klakow*24 citations*
20. **[Interpretable Neural Architectures for Attributing an Ad's Performance to its Writing Style ↗](https://aclanthology.org/W18-5415/)**Reid Pryzant, Sugato Basu, Kazoo Sone*22 citations*
21. **[LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation ↗](https://aclanthology.org/W18-5418/)**Pankaj Gupta, Hinrich Schütze*22 citations*
22. **[Analyzing Learned Representations of a Deep ASR Performance Prediction Model ↗](https://aclanthology.org/W18-5402/)**Zied Elloumi, Laurent Besacier, Olivier Galibert et al.*21 citations*
23. **[Interpretable Textual Neuron Representations for NLP ↗](https://aclanthology.org/W18-5437/)**Nina Poerner, Benjamin Roth, Hinrich Schütze*21 citations*
24. **[Predicting and interpreting embeddings for out of vocabulary words in downstream tasks ↗](https://aclanthology.org/W18-5439/)**Nicolas Garneau, Jean-Samuel Leboeuf, Luc Lamontagne*21 citations*
25. **[Grammar Induction with Neural Language Models: An Unusual Replication ↗](https://aclanthology.org/W18-5452/)**Phu Mon Htut, Kyunghyun Cho, Samuel R. Bowman*17 citations*
26. **[Introspection for convolutional automatic speech recognition ↗](https://aclanthology.org/W18-5421/)**Andreas Krug, Sebastian Stober*16 citations*
27. **[Interpretable Structure Induction via Sparse Attention ↗](https://aclanthology.org/W18-5450/)**Ben Peters, Vlad Niculae, André F. T. Martins*15 citations*
28. **[Learning and Evaluating Sparse Interpretable Sentence Embeddings ↗](https://aclanthology.org/W18-5422/)**Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko et al.*15 citations*
29. **[Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures ↗](https://aclanthology.org/W18-5403/)**Danilo Croce, Daniele Rossini, Roberto Basili*14 citations*
30. **[Nightmare at test time: How punctuation prevents parsers from generalizing ↗](https://aclanthology.org/W18-5404/)**Anders Søgaard, Miryam de Lhoneux, Isabelle Augenstein*14 citations*
31. **[`Indicatements' that character language models learn English morpho-syntactic units and regularities ↗](https://aclanthology.org/W18-5417/)**Yova Kementchedjhieva, Adam Lopez*12 citations*
32. **[Iterative Recursive Attention Model for Interpretable Sequence Classification ↗](https://aclanthology.org/W18-5427/)**Martin Tutek, Jan Šnajder*11 citations*
33. **[Language Models Learn POS First ↗](https://aclanthology.org/W18-5438/)**Naomi Saphra, Adam Lopez*11 citations*
34. **[Evaluating Textual Representations through Image Generation ↗](https://aclanthology.org/W18-5405/)**Graham Spinks, Marie-Francine Moens*10 citations*
35. **[Debugging Sequence-to-Sequence Models with Seq2Seq-Vis ↗](https://aclanthology.org/W18-5451/)**Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch et al.*9 citations*
36. **[Exploiting Attention to Reveal Shortcomings in Memory Models ↗](https://aclanthology.org/W18-5454/)**Kaylee Burns, Aida Nematzadeh, Erin Grant et al.*9 citations*
37. **[Learning Explanations from Language Data ↗](https://aclanthology.org/W18-5434/)**David Harbecke, Robert Schwarzenberg, Christoph Alt*9 citations*
38. **[End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space ↗](https://aclanthology.org/W18-5455/)**Pranava Swaroop Madhyastha, Josiah Wang, Lucia Specia*8 citations*
39. **[Linguistic representations in multi-task neural networks for ellipsis resolution ↗](https://aclanthology.org/W18-5409/)**Ola Rønning, Daniel Hardt, Anders Søgaard*8 citations*
40. **[Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models ↗](https://aclanthology.org/W18-5428/)**Avery Hiebert, Cole Peterson, Alona Fyshe et al.*7 citations*
41. **[Probing sentence embeddings for structure-dependent tense ↗](https://aclanthology.org/W18-5440/)**Geoff Bacon, Terry Regier*7 citations*
42. **[State Gradients for RNN Memory Analysis ↗](https://aclanthology.org/W18-5443/)**Lyan Verwimp, Hugo Van hamme, Vincent Renkens et al.*7 citations*
43. **[Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models ↗](https://aclanthology.org/W18-5410/)**Shun Kiyono, Sho Takase, Jun Suzuki et al.*7 citations*
44. **[Analysing the potential of seq-to-seq models for incremental interpretation in task-oriented dialogue ↗](https://aclanthology.org/W18-5419/)**Dieuwke Hupkes, Sanne Bouwmeester, Raquel Fernández*6 citations*
45. **[Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information ↗](https://aclanthology.org/W18-5426/)**Mario Giulianelli, Jack Harding, Florian Mohnert et al.*6 citations*
46. **[When does deep multi-task learning work for loosely related document classification tasks? ↗](https://aclanthology.org/W18-5401/)**Emma Kerinec, Chloé Braud, Anders Søgaard*6 citations*
47. **[Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System ↗](https://aclanthology.org/W18-5436/)**Barbara Rychalska, Dominika Basaj, Anna Wróblewska et al.*5 citations*
48. **[Jump to better conclusions: SCAN both left and right ↗](https://aclanthology.org/W18-5407/)**Jasmijn Bastings, Marco Baroni, Jason Weston et al.*5 citations*
49. **[Limitations in learning an interpreted language with recurrent models ↗](https://aclanthology.org/W18-5456/)**Denis Paperno*5 citations*
50. **[Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation ↗](https://aclanthology.org/W18-5432/)**Johnny Wei, Khiem Pham, Brendan O'Connor et al.*3 citations*
51. **[Explicitly modeling case improves neural dependency parsing ↗](https://aclanthology.org/W18-5447/)**Clara Vania, Adam Lopez*2 citations*
52. **[How much should you ask? On the question structure in QA systems. ↗](https://aclanthology.org/W18-5435/)**Barbara Rychalska, Dominika Basaj, Anna Wróblewska et al.*2 citations*
53. **[Interpretable Word Embedding Contextualization ↗](https://aclanthology.org/W18-5442/)**Kyoung-Rok Jang, Sung-Hyon Myaeng, Sang-Bum Kim*2 citations*
54. **[Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model ↗](https://aclanthology.org/W18-5449/)**Steven Derby, Paul Miller, Brian Murphy et al.*2 citations*
55. **[Rule induction for global explanation of trained models ↗](https://aclanthology.org/W18-5411/)**Madhumita Sushil, Simon Šuster, Walter Daelemans*2 citations*
56. **[Portable, layer-wise task performance monitoring for NLP models ↗](https://aclanthology.org/W18-5445/)**Tom Lippincott
- [← back to](https://md.research.elamur.ai/free/en/venues/emnlp-workshop-blackboxnlp-analyzing-and-interpreting-neural-networks-for-nlp/2018/) — EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP 2018