 Numerical Optimizations for Weighted Low-rank Estimation on Language
ModelConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Modeling structure-building in the brain with CCG parsing and large
language modelsCognitive Sciences (CS), 2022 |
 Benchmarking Language Models for Code Syntax UnderstandingConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Hidden State Variability of Pretrained Language Models Can Guide
Computation Reduction for Transfer LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Token Merging: Your ViT But FasterInternational Conference on Learning Representations (ICLR), 2022 |
 Shapley Head Pruning: Identifying and Removing Interference in
Multilingual TransformersConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 William B. Held Diyi Yang |
 Mixture of Attention Heads: Selecting Attention Heads Per TokenConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Parameter-Efficient Tuning with Special Token AdaptationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 Better Pre-Training by Reducing Representation ConfusionFindings (Findings), 2022 |
 Masked Spiking TransformerIEEE International Conference on Computer Vision (ICCV), 2022 |
 Towards Faithful Model Explanation in NLP: A SurveyComputational Linguistics (CL), 2022 |
 Relaxed Attention for Transformer ModelsIEEE International Joint Conference on Neural Network (IJCNN), 2022 |
 Analysis of Self-Attention Head Diversity for Conformer-based Automatic
Speech RecognitionInterspeech (Interspeech), 2022 |
 Analyzing Transformers in Embedding SpaceAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Efficient Methods for Natural Language Processing: A SurveyTransactions of the Association for Computational Linguistics (TACL), 2022 |
 SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad RelevanceInternational Conference on Information and Knowledge Management (CIKM), 2022 |
 Survey: Exploiting Data Redundancy for Optimization of Deep LearningACM Computing Surveys (ACM CSUR), 2022 |
 Combining Compressions for Multiplicative Size Scaling on Natural
Language TasksInternational Conference on Computational Linguistics (COLING), 2022 |
 Looking for a Needle in a Haystack: A Comprehensive Study of
Hallucinations in Neural Machine TranslationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised
Semantic SegmentationPattern Recognition (Pattern Recogn.), 2022 |
 STI: Turbocharge NLP Inference at the Edge via Elastic PipeliningInternational Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2022 |
 Probing via PromptingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Discovering Salient Neurons in Deep NLP ModelsJournal of machine learning research (JMLR), 2022 |
 Visualizing and Understanding Contrastive LearningIEEE Transactions on Image Processing (IEEE TIP), 2022 |
 Optimizing Relevance Maps of Vision Transformers Improves RobustnessNeural Information Processing Systems (NeurIPS), 2022 |
 Life after BERT: What do Other Muppets Understand about Language?Annual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Exploring Extreme Parameter Compression for Pre-trained Language ModelsInternational Conference on Learning Representations (ICLR), 2022 |
 Foundation Posteriors for Approximate Probabilistic InferenceNeural Information Processing Systems (NeurIPS), 2022 |
 Acceptability Judgements via Examining the Topology of Attention MapsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
