default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCID5th BlackboxNLP@EMNLP 2022: Abu Dhabi, United Arab Emirates (Hybrid)
- Jasmijn Bastings, Yonatan Belinkov, Yanai Elazar, Dieuwke Hupkes, Naomi Saphra, Sarah Wiegreffe:
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2022, Abu Dhabi, United Arab Emirates (Hybrid), December 8, 2022. Association for Computational Linguistics 2022, ISBN 978-1-959429-05-0 - Alice Hein
, Klaus Diepold:
A Minimal Model for Compositional Generalization on gSCAN. 1-15 - Nicola De Cao, Leon Schmid, Dieuwke Hupkes, Ivan Titov:
Sparse Interventions in Language Models with Differentiable Masking. 16-27 - Mughilan Muthupari, Samrat Halder, Asad B. Sayeed, Yuval Marton:
Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit. 28-39 - Sunit Bhattacharya, Vilém Zouhar, Ondrej Bojar:
Sentence Ambiguity, Grammaticality and Complexity Probes. 40-50 - Kiron Deb, Xuan Zhang, Kevin Duh:
Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines. 51-61 - Ning Shi, Boxin Wang, Wei Wang, Xiangyu Liu, Zhouhan Lin:
Revisit Systematic Generalization via Meaningful Learning. 62-79 - Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, Walter Daelemans:
Is It Smaller Than a Tennis Ball? Language Models Play the Game of Twenty Questions. 80-90 - Ahmed Abdelali, Nadir Durrani, Fahim Dalvi, Hassan Sajjad:
Post-hoc analysis of Arabic transformer models. 91-103 - Wenchuan Mu, Kwan Hui Lim:
Universal Evasion Attacks on Summarization Scoring. 104-118 - Hessam Amini, Leila Kosseim:
How (Un)Faithful is Attention? 119-130 - Rasmus Kær Jørgensen, Fiammetta Caccavale, Christian Igel, Anders Søgaard:
Are Multilingual Sentiment Models Equally Right for the Right Reasons? 131-141 - David K. Yi, James V. Bruno, Jiayu Han, Peter Zukerman, Shane Steinert-Threlkeld:
Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models. 142-152 - Guillaume Wisniewski, Lichao Zhu, Nicolas Ballier, François Yvon:
Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT System. 153-163 - Jenny Kunz, Martin Jirenius, Oskar Holmström, Marco Kuhlmann:
Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions. 164-177 - Badr Abdullah, Dietrich Klakow:
Analyzing the Representational Geometry of Acoustic Word Embeddings. 178-191 - Zheng Zhao, Yftah Ziser, Shay B. Cohen:
Understanding Domain Learning in Language Models Through Subpopulation Analysis. 192-209 - Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh, Byron C. Wallace:
Intermediate Entity-based Sparse Interpretable Representation Learning. 210-224 - Isar Nejadgholi, Esma Balkir, Kathleen C. Fraser, Svetlana Kiritchenko:
Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information. 225-237 - Digvijay Ingle, Rishabh Kumar Tripathi, Ayush Kumar, Kevin Patel, Jithendra Vepa:
Investigating the Characteristics of a Transformer in a Few-Shot Setup: Does Freezing Layers in RoBERTa Help? 238-248 - Teemu Vahtola, Mathias Creutz, Jörg Tiedemann:
It Is Not Easy To Detect Paraphrases: Analysing Semantic Similarity With Antonyms and Negation Using the New SemAntoNeg Benchmark. 249-262 - Manuj Malik, Richard Johansson:
Controlling for Stereotypes in Multimodal Language Model Evaluation. 263-271 - Arian Hosseini, Ankit Vani, Dzmitry Bahdanau, Alessandro Sordoni, Aaron C. Courville:
On the Compositional Generalization Gap of In-Context Learning. 272-280 - Kwabena Amponsah-Kaakyire, Daria Pylypenko, Josef van Genabith, Cristina España-Bonet:
Explaining Translationese: why are Neural Classifiers Better and what do they Learn? 281-296 - Lining Zhang, Mengchen Wang, Liben Chen, Wenxin Zhang:
Probing GPT-3's Linguistic Knowledge on Semantic Tasks. 297-304 - William Jurayj, William Rudman, Carsten Eickhoff:
Garden Path Traversal in GPT-2. 305-313 - Pangbo Ban, Yifan Jiang, Tianran Liu, Shane Steinert-Threlkeld:
Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis. 314-324 - Jingcheng Niu, Wenjie Lu, Eric Corlett, Gerald Penn:
Using Roark-Hollingshead Distance to Probe BERT's Syntactic Competence. 325-334 - Royi Rassin, Shauli Ravfogel, Yoav Goldberg:
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models. 335-345 - Anurag Katakkar, Clay H. Yoo, Weiqin Wang, Zachary C. Lipton, Divyansh Kaushik:
Practical Benefits of Feature Feedback Under Distribution Shift. 346-355 - Ruixuan Tang, Hanjie Chen, Yangfeng Ji:
Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification. 356-370 - Sergey Troshin, Nadezhda Chirkova:
Probing Pretrained Models of Source Codes. 371-383 - Stefan F. Schouten, Peter Bloem, Piek Vossen:
Probing the representations of named entities in Transformer-based Language Models. 384-393 - Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas:
Decomposing Natural Logic Inferences for Neural NLI. 394-403 - Filip Klubicka, John D. Kelleher:
Probing with Noise: Unpicking the Warp and Weft of Embeddings. 404-417 - Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa:
Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering. 418-425 - Darcey Riley, David Chiang:
A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition. 426-440 - Oleg Serikov, Vitaly Protasov, Ekaterina Voloshina, Viktoria Knyazkova, Tatiana Shavrina:
Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation. 441-456
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-12-15 22:35 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
