{"total":18,"rows":[{"id":"2210.03797","title":"Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts","created":"2022-10-07","cited_by_count":28,"area":null},{"id":"2109.04607","title":"IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization","created":"2021-09-10","cited_by_count":25,"area":null},{"id":"2310.16484","title":"Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2201.07281","title":"Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis","created":"2022-01-18","cited_by_count":9,"area":null},{"id":"2403.12749","title":"Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2104.08659","title":"Monotonicity Marking from Universal Dependency Trees","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2209.13778","title":"Data-driven Parsing Evaluation for Child-Parent Interactions","created":"2022-09-28","cited_by_count":3,"area":null},{"id":"2106.04935","title":"Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2204.10621","title":"Out-of-Domain Evaluation of Finnish Dependency Parsing","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2305.12634","title":"Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2412.09587","title":"OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languages","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2102.11152","title":"Creating a Universal Dependencies Treebank of Spoken Frisian-Dutch Code-switched Data","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2109.07483","title":"Cross-Register Projection for Headline Part of Speech Tagging","created":"2021-09-15","cited_by_count":1,"area":null},{"id":"2304.13567","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2601.16623","title":"MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2209.11959","title":"TransPOS: Transformers for Consolidating Different POS Tagset Datasets","created":"2022-09-24","cited_by_count":0,"area":null},{"id":"2301.10371","title":"Weakly Supervised Headline Dependency Parsing","created":"2023-01-25","cited_by_count":0,"area":null},{"id":"2307.10210","title":"Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data","created":"2023-07-14","cited_by_count":0,"area":null}],"next_cursor":null}