 An information theoretic view on selecting linguistic probesConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 |
 Compositional Explanations of NeuronsNeural Information Processing Systems (NeurIPS), 2020 |
 Revisiting Few-sample BERT Fine-tuningInternational Conference on Learning Representations (ICLR), 2020 |
 Emergence of Separable Manifolds in Deep Language RepresentationsInternational Conference on Machine Learning (ICML), 2020 |
 Syntactic Structure Distillation Pretraining For Bidirectional EncodersTransactions of the Association for Computational Linguistics (TACL), 2020 |
 A Tale of a Probe and a ParserAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Emergence of Syntax Needs Minimal SupervisionAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Interpretable Entity Representations through Large-Scale TypingFindings (Findings), 2020 |
 A Matter of Framing: The Impact of Linguistic Formalism on Probing
ResultsConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 Ilia Kuznetsov Iryna Gurevych |
 Asking without Telling: Exploring Latent Ontologies in Contextual
RepresentationsConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 What Happens To BERT Embeddings During Fine-tuning?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP), 2020 |
 Do Neural Language Models Show Preferences for Syntactic Formalisms?Annual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Quantifying the Contextualization of Word Representations with Semantic
Class ProbingFindings (Findings), 2020 |
 Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent
Neural NetworksNordic Conference of Computational Linguistics (NODALIDA), 2020 |
 Information-Theoretic Probing with Minimum Description LengthConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 |
 Parsing as PretrainingAAAI Conference on Artificial Intelligence (AAAI), 2020 |
 What Does My QA Model Know? Devising Controlled Probes using Expert
KnowledgeTransactions of the Association for Computational Linguistics (TACL), 2019 |
 oLMpics -- On what Language Model Pre-training CapturesTransactions of the Association for Computational Linguistics (TACL), 2019 |
