{"total":16,"rows":[{"id":"2106.00218","title":"Discontinuous Named Entity Recognition as Maximal Clique Discovery","created":"2021-06-01","cited_by_count":17,"area":null},{"id":"2311.01038","title":"Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2104.08078","title":"To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2210.10951","title":"Automatic Document Selection for Efficient Encoder Pretraining","created":"2022-10-20","cited_by_count":11,"area":null},{"id":"2109.04733","title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2109.06605","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2109.07140","title":"On the Universality of Deep Contextual Language Models","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2112.04971","title":"How Universal is Genre in Universal Dependencies?","created":"2021-12-09","cited_by_count":4,"area":null},{"id":"2212.07914","title":"The Effects of In-domain Corpus Size on pre-training BERT","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2401.08715","title":"Selecting Subsets of Source Data for Transfer Learning with Applications in Metal Additive Manufacturing","created":"2024-01-16","cited_by_count":3,"area":null},{"id":"2205.01749","title":"Mixed-effects transformers for hierarchical adaptation","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2206.04935","title":"Sort by Structure: Language Model Ranking as Dependency Probing","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2403.10576","title":"Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2311.08793","title":"German FinBERT: A German Pre-trained Language Model","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2111.06664","title":"Extraction of Medication Names from Twitter Using Augmentation and an Ensemble of Language Models","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2310.18944","title":"S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition","created":"2023-10-29","cited_by_count":0,"area":null}],"next_cursor":null}