Designing and Interpreting Probes with Control Tasks

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019

8 September 2019

Papers citing "Designing and Interpreting Probes with Control Tasks"

50 / 381 papers shown

Title
On the Pitfalls of Analyzing Individual Neurons in Language Models Omer Antverg Yonatan Belinkov MILM 232 62 0 14 Oct 2021
Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic FactorsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Marvin Kaster Wei Zhao Steffen Eger 248 29 0 08 Oct 2021
BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification Zeguan Xiao Jiarun Wu Qingliang Chen Congjian Deng 138 87 0 01 Oct 2021
Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations Ekaterina Taktasheva Vladislav Mikhailov Ekaterina Artemova 211 14 0 28 Sep 2021
Awakening Latent Grounding from Pretrained Language Models for Semantic ParsingFindings (Findings), 2021 Qian Liu Dejian Yang Jiahui Zhang Jiaqi Guo Bin Zhou Jian-Guang Lou 165 42 0 22 Sep 2021
Conditional probing: measuring usable information beyond a baseline John Hewitt Kawin Ethayarajh Abigail Z. Jacobs Christopher D. Manning 172 63 0 19 Sep 2021
Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information? Julia Rozanova Deborah Ferreira K. Dubba Weiwei Cheng Dell Zhang André Freitas LM&Ro 142 12 0 17 Sep 2021
Adversarial Scrubbing of Demographic Information for Text Classification Somnath Basu Roy Chowdhury Sayan Ghosh Yiyuan Li Junier B. Oliva Shashank Srivastava Snigdha Chaturvedi 148 15 0 17 Sep 2021
Do Language Models Know the Way to Rome? Bastien Liétard Mostafa Abdou Anders Søgaard 211 26 0 16 Sep 2021
Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models? Sagnik Ray Choudhury Nikita Bhutani Isabelle Augenstein 297 1 0 15 Sep 2021
The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders Han He Jinho Choi 252 126 0 14 Sep 2021
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color Mostafa Abdou Artur Kulmizev Daniel Hershcovich Stella Frank Ellie Pavlick Anders Søgaard 194 156 0 13 Sep 2021
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations Mohsen Fayyaz Ehsan Aghazadeh Ali Modarressi Hosein Mohebbi Mohammad Taher Pilehvar 156 21 0 13 Sep 2021
Debiasing Methods in Natural Language Understanding Make Bias More AccessibleConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Michael J. Mendelson Yonatan Belinkov 185 27 0 09 Sep 2021
A Bayesian Framework for Information-Theoretic ProbingConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Tiago Pimentel Robert Bamler 219 25 0 08 Sep 2021
How much pretraining data do language models need to learn syntax?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Laura Pérez-Mayos Miguel Ballesteros Leo Wanner 133 36 0 07 Sep 2021
How Does Adversarial Fine-Tuning Benefit BERT? J. Ebrahimi Hao Yang Wei Zhang AAML 217 5 0 31 Aug 2021
Neuron-level Interpretation of Deep NLP Models: A SurveyTransactions of the Association for Computational Linguistics (TACL), 2021 Hassan Sajjad Nadir Durrani Fahim Dalvi MILM AI4CE 301 94 0 30 Aug 2021
Automatic Text Evaluation through the Lens of Wasserstein BarycentersConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Pierre Colombo Guillaume Staerman Chloé Clavel Pablo Piantanida 357 43 0 27 Aug 2021
What can Neural Referential Form Selectors Learn? Guanyi Chen F. Same Kees van Deemter 132 6 0 15 Aug 2021
Post-hoc Interpretability for Neural NLP: A SurveyACM Computing Surveys (CSUR), 2021 Andreas Madsen Siva Reddy A. Chandar XAI 337 276 0 10 Aug 2021
FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field AttentionNeural Information Processing Systems (NeurIPS), 2021 T. Nguyen Vai Suliafu Stanley J. Osher Long Chen Bao Wang 141 38 0 05 Aug 2021
Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning Vivek Gupta Riyaz Ahmad Bhat Atreya Ghosal Manisha Srivastava M. Singh Vivek Srikumar LMTD 243 19 0 02 Aug 2021
Using a Cross-Task Grid of Linear Probes to Interpret CNN Model Predictions On Retinal Images Katy Blumer Subhashini Venugopalan Michael P. Brenner Jon M. Kleinberg 70 0 0 23 Jul 2021
What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis Shammur A. Chowdhury Nadir Durrani Ahmed M. Ali 344 20 0 01 Jul 2021
A Closer Look at How Fine-tuning Changes BERTAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Yichu Zhou Vivek Srikumar 264 77 0 27 Jun 2021
Visual Probing: Cognitive Framework for Explaining Self-Supervised Image RepresentationsIEEE Access (IEEE Access), 2021 Witold Oleszkiewicz Dominika Basaj Igor Sieradzki Michal Górszczak Barbara Rychalska K. Lewandowska Tomasz Trzciñski Bartosz Zieliñski SSL 175 3 0 21 Jun 2021
Biomedical Interpretable Entity RepresentationsFindings (Findings), 2021 Diego Garcia-Olano Yasumasa Onoe Ioana Baldini Joydeep Ghosh Byron C. Wallace Kush R. Varshney AI4CE 185 3 0 17 Jun 2021
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Matthew Finlayson Aaron Mueller Sebastian Gehrmann Stuart M. Shieber Tal Linzen Yonatan Belinkov 345 134 0 10 Jun 2021
Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic DatasetsWorkshop on Representation Learning for NLP (RepL4NLP), 2021 Lan Zhang Victor Prokhorov Ehsan Shareghi CoGe DRL 105 3 0 07 Jun 2021
Causal Abstractions of Neural NetworksNeural Information Processing Systems (NeurIPS), 2021 Atticus Geiger Hanson Lu Thomas Icard Christopher Potts NAI CML 330 302 0 06 Jun 2021
Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-TuningAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Forrest Davis Marten van Schijndel AI4CE 204 7 0 02 Jun 2021
Implicit Representations of Meaning in Neural Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Belinda Z. Li Maxwell Nye Jacob Andreas NAI MILM 255 208 0 01 Jun 2021
Language Model Evaluation Beyond PerplexityAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Clara Meister Robert Bamler 439 99 0 31 May 2021
How transfer learning impacts linguistic knowledge in deep NLP models?Findings (Findings), 2021 Nadir Durrani Hassan Sajjad Fahim Dalvi 146 53 0 31 May 2021
What if This Modified That? Syntactic Interventions via Counterfactual EmbeddingsFindings (Findings), 2021 Mycal Tucker Peng Qian R. Levy 242 47 0 28 May 2021
Language Models Use Monotonicity to Assess NPI LicensingFindings (Findings), 2021 Jaap Jumelet Milica Denić Jakub Szymanik Dieuwke Hupkes Shane Steinert-Threlkeld KELM 161 31 0 28 May 2021
A Non-Linear Structural ProbeNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 Jennifer C. White Tiago Pimentel Naomi Saphra Robert Bamler 136 32 0 21 May 2021
Fine-grained Interpretation and Causation Analysis in Deep NLP ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 Hassan Sajjad Narine Kokhlikyan Fahim Dalvi Nadir Durrani MILM 297 8 0 17 May 2021
The Low-Dimensional Linear Geometry of Contextualized Word RepresentationsConference on Computational Natural Language Learning (CoNLL), 2021 Evan Hernandez Jacob Andreas MILM 208 53 0 15 May 2021
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement PredictionConference on Computational Natural Language Learning (CoNLL), 2021 Shauli Ravfogel Grusha Prasad Tal Linzen Yoav Goldberg 253 67 0 14 May 2021
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance LevelFindings (Findings), 2021 Ruiqi Zhong Dhruba Ghosh Dan Klein Jacob Steinhardt 154 42 0 13 May 2021
How Reliable are Model Diagnostics?Findings (Findings), 2021 V. Aribandi Yi Tay Donald Metzler 125 19 0 12 May 2021
FNet: Mixing Tokens with Fourier TransformsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 James Lee-Thorp Joshua Ainslie Ilya Eckstein Santiago Ontanon 592 632 0 09 May 2021
Bird's Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic ApproachAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Buse Giledereli Mrinmaya Sachan 228 11 0 06 May 2021
Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into SensesTransactions of the Association for Computational Linguistics (TACL), 2021 Aina Garí Soler Marianna Apidianaki MILM 400 76 0 29 Apr 2021
Morph Call: Probing Morphosyntactic Content of Multilingual Transformers Vladislav Mikhailov O. Serikov Ekaterina Artemova 228 10 0 26 Apr 2021
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?Transactions of the Association for Computational Linguistics (TACL), 2021 William Merrill Yoav Goldberg Roy Schwartz Noah A. Smith 302 75 0 22 Apr 2021
Linguistic Dependencies and Statistical DependenceConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Jacob Louis Hoover Alessandro Sordoni Wenyu Du Timothy J. O'Donnell 303 17 0 18 Apr 2021
A multilabel approach to morphosyntactic probingConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Naomi Tachikawa Shapiro Amandalynne Paullada Shane Steinert-Threlkeld 209 11 0 17 Apr 2021