{"total":34,"rows":[{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2211.06651","title":"NLPeer: A Unified Resource for the Computational Study of Peer Review","created":"2022-11-12","cited_by_count":60,"area":null},{"id":"2109.11406","title":"Named Entity Recognition and Classification on Historical Documents: A Survey","created":"2021-09-23","cited_by_count":47,"area":null},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","cited_by_count":25,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2306.01966","title":"GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation","created":"2023-06-03","cited_by_count":19,"area":null},{"id":"2201.11443","title":"Yes-Yes-Yes: Proactive Data Collection for ACL Rolling Review and Beyond","created":"2022-01-27","cited_by_count":12,"area":null},{"id":"2307.02740","title":"Dense Retrieval Adaptation using Target Domain Description","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2111.01340","title":"Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks","created":"2021-11-02","cited_by_count":6,"area":null},{"id":"2203.16169","title":"Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling","created":"2022-03-30","cited_by_count":6,"area":null},{"id":"2403.01983","title":"Language and Speech Technology for Central Kurdish Varieties","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2109.04876","title":"Integrating Approaches to Word Representation","created":"2021-09-10","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":"2203.10123","title":"Event Coreference Resolution for Contentious Politics Events","created":"2022-03-18","cited_by_count":4,"area":null},{"id":"2210.12553","title":"Understanding Domain Learning in Language Models Through Subpopulation Analysis","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2503.18247","title":"AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2407.13141","title":"Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression","created":"2024-07-18","cited_by_count":3,"area":null},{"id":"2501.16836","title":"Misspellings in Natural Language Processing: A survey","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2503.14718","title":"Second language Korean Universal Dependency treebank v1.2: Focus on data augmentation and annotation scheme refinement","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2204.04534","title":"Extending the Scope of Out-of-Domain: Examining QA models in multiple subdomains","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2404.01785","title":"Can Humans Identify Domains?","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2410.14589","title":"Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2411.12458","title":"Variation between Credible and Non-Credible News Across Topics","created":"2024-11-19","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":"2211.05604","title":"An Inclusive Notion of Text","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2408.11926","title":"Defining Boundaries: The Impact of Domain Specification on Cross-Language and Cross-Domain Transfer in Machine Translation","created":"2024-08-21","cited_by_count":0,"area":null},{"id":"2602.12759","title":"Towards a Diagnostic and Predictive Evaluation Methodology for Sequence Labeling Tasks","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.24222","title":"Variation is the Norm: Embracing Sociolinguistics in NLP","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2605.06625","title":"Parser agreement and disagreement in L2 Korean UD: Implications for human-in-the-loop annotation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2609.27205","title":"Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}