{"total":18,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2204.10050","title":"SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding","created":"2022-04-21","cited_by_count":36,"area":null},{"id":"2405.07883","title":"Zero-Shot Tokenizer Transfer","created":"2024-05-13","cited_by_count":31,"area":null},{"id":"2206.03352","title":"Searching for Optimal Subword Tokenization in Cross-domain NER","created":"2022-06-07","cited_by_count":17,"area":null},{"id":"2411.18553","title":"Retrofitting Large Language Models with Dynamic Tokenization","created":"2024-11-27","cited_by_count":16,"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":"2402.14616","title":"The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations","created":"2024-02-22","cited_by_count":6,"area":null},{"id":"2505.20133","title":"Token Distillation: Attention-aware Input Embeddings For New Tokens","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2204.02821","title":"drsphelps at SemEval-2022 Task 2: Learning idiom representations using BERTRAM","created":"2022-04-06","cited_by_count":5,"area":null},{"id":"2109.11763","title":"Lacking the embedding of a word? Look it up into a traditional dictionary","created":"2021-09-24","cited_by_count":4,"area":null},{"id":"2205.11306","title":"Sample Efficient Approaches for Idiomaticity Detection","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2504.21018","title":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2103.03842","title":"Overcoming Poor Word Embeddings with Word Definitions","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2302.07324","title":"READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2401.07977","title":"Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2605.13429","title":"TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2306.01443","title":"Unsupervised Paraphrasing of Multiword Expressions","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2610.18672","title":"SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}