Designing and Interpreting Probes with Control Tasks

8 September 2019

Papers citing "Designing and Interpreting Probes with Control Tasks"

42 / 92 papers shown

Title
Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs Peter Hase Mona T. Diab Asli Celikyilmaz Xian Li Zornitsa Kozareva Veselin Stoyanov Mohit Bansal Srini Iyer KELM LRM 19 79 0 26 Nov 2021
Interpreting Deep Learning Models in Natural Language Processing: A Review Xiaofei Sun Diyi Yang Xiaoya Li Tianwei Zhang Yuxian Meng Han Qiu Guoyin Wang Eduard H. Hovy Jiwei Li 17 44 0 20 Oct 2021
On the Pitfalls of Analyzing Individual Neurons in Language Models Omer Antverg Yonatan Belinkov MILM 22 49 0 14 Oct 2021
Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors Marvin Kaster Wei-Ye Zhao Steffen Eger 19 24 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 19 71 0 01 Oct 2021
Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing Qian Liu Dejian Yang Jiahui Zhang Jiaqi Guo Bin Zhou Jian-Guang Lou 48 41 0 22 Sep 2021
Conditional probing: measuring usable information beyond a baseline John Hewitt Kawin Ethayarajh Percy Liang Christopher D. Manning 31 55 0 19 Sep 2021
The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders Han He Jinho D. Choi 43 87 0 14 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 18 21 0 13 Sep 2021
Debiasing Methods in Natural Language Understanding Make Bias More Accessible Michael J. Mendelson Yonatan Belinkov 38 23 0 09 Sep 2021
How Does Adversarial Fine-Tuning Benefit BERT? J. Ebrahimi Hao Yang Wei Zhang AAML 18 4 0 31 Aug 2021
Neuron-level Interpretation of Deep NLP Models: A Survey Hassan Sajjad Nadir Durrani Fahim Dalvi MILM AI4CE 24 79 0 30 Aug 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 25 12 0 01 Jul 2021
A Closer Look at How Fine-tuning Changes BERT Yichu Zhou Vivek Srikumar 24 63 0 27 Jun 2021
How transfer learning impacts linguistic knowledge in deep NLP models? Nadir Durrani Hassan Sajjad Fahim Dalvi 13 48 0 31 May 2021
How Reliable are Model Diagnostics? V. Aribandi Yi Tay Donald Metzler 19 19 0 12 May 2021
Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses Aina Garí Soler Marianna Apidianaki MILM 201 68 0 29 Apr 2021
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? William Merrill Yoav Goldberg Roy Schwartz Noah A. Smith 17 67 0 22 Apr 2021
A multilabel approach to morphosyntactic probing Naomi Tachikawa Shapiro Amandalynne Paullada Shane Steinert-Threlkeld 27 10 0 17 Apr 2021
What's in your Head? Emergent Behaviour in Multi-Task Transformer Models Mor Geva Uri Katz Aviv Ben-Arie Jonathan Berant LRM 35 11 0 13 Apr 2021
DirectProbe: Studying Representations without Classifiers Yichu Zhou Vivek Srikumar 27 27 0 13 Apr 2021
NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance Aarne Talman Marianna Apidianaki S. Chatzikyriakidis Jörg Tiedemann 20 10 0 10 Apr 2021
Local Interpretations for Explainable Natural Language Processing: A Survey Siwen Luo Hamish Ivison S. Han Josiah Poon MILM 33 48 0 20 Mar 2021
The Rediscovery Hypothesis: Language Models Need to Meet Linguistics Vassilina Nikoulina Maxat Tezekbayev Nuradil Kozhakhmet Madina Babazhanova Matthias Gallé Z. Assylbekov 29 8 0 02 Mar 2021
Contrastive Explanations for Model Interpretability Alon Jacovi Swabha Swayamdipta Shauli Ravfogel Yanai Elazar Yejin Choi Yoav Goldberg 33 95 0 02 Mar 2021
Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case Adam Dahlgren Lindström Suna Bensch Johanna Björklund F. Drewes 16 20 0 22 Feb 2021
Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers Lisa Anne Hendricks John F. J. Mellor R. Schneider Jean-Baptiste Alayrac Aida Nematzadeh 75 110 0 31 Jan 2021
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT Benjamin Muller Yanai Elazar Benoît Sagot Djamé Seddah LRM 21 71 0 26 Jan 2021
Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT Isabel Papadimitriou Ethan A. Chi Richard Futrell Kyle Mahowald 19 44 0 26 Jan 2021
When Do You Need Billions of Words of Pretraining Data? Yian Zhang Alex Warstadt Haau-Sing Li Samuel R. Bowman 21 136 0 10 Nov 2020
Linguistic Profiling of a Neural Language Model Alessio Miaschi D. Brunato F. Dell’Orletta Giulia Venturi 25 46 0 05 Oct 2020
Examining the rhetorical capacities of neural language models Zining Zhu Chuer Pan Mohamed Abdalla Frank Rudzicz 28 10 0 01 Oct 2020
Revisiting Few-sample BERT Fine-tuning Tianyi Zhang Felix Wu Arzoo Katiyar Kilian Q. Weinberger Yoav Artzi 30 441 0 10 Jun 2020
Syntactic Structure Distillation Pretraining For Bidirectional Encoders A. Kuncoro Lingpeng Kong Daniel Fried Dani Yogatama Laura Rimell Chris Dyer Phil Blunsom 31 33 0 27 May 2020
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions Xiaochuang Han Byron C. Wallace Yulia Tsvetkov MILM FAtt AAML TDI 18 164 0 14 May 2020
Finding Universal Grammatical Relations in Multilingual BERT Ethan A. Chi John Hewitt Christopher D. Manning 13 151 0 09 May 2020
Probing Contextual Language Models for Common Ground with Visual Representations Gabriel Ilharco Rowan Zellers Ali Farhadi Hannaneh Hajishirzi 22 14 0 01 May 2020
Information-Theoretic Probing with Minimum Description Length Elena Voita Ivan Titov 19 269 0 27 Mar 2020
Parsing as Pretraining David Vilares Michalina Strzyz Anders Søgaard Carlos Gómez-Rodríguez 28 31 0 05 Feb 2020
oLMpics -- On what Language Model Pre-training Captures Alon Talmor Yanai Elazar Yoav Goldberg Jonathan Berant LRM 17 300 0 31 Dec 2019
What do you mean, BERT? Assessing BERT as a Distributional Semantics Model Timothee Mickus Denis Paperno Mathieu Constant Kees van Deemter 18 45 0 13 Nov 2019
What you can cram into a single vector: Probing sentence embeddings for linguistic properties Alexis Conneau Germán Kruszewski Guillaume Lample Loïc Barrault Marco Baroni 199 882 0 03 May 2018