{"total":31,"rows":[{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2101.03289","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","created":"2021-01-09","cited_by_count":68,"area":null},{"id":"2109.07020","title":"Frequency Effects on Syntactic Rule Learning in Transformers","created":"2021-09-14","cited_by_count":59,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31,"area":null},{"id":"2109.10534","title":"Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages","created":"2021-09-22","cited_by_count":24,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2404.01574","title":"Multi-granular Adversarial Attacks against Black-box Neural Ranking Models","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2103.15261","title":"One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks","created":"2021-03-29","cited_by_count":8,"area":null},{"id":"2307.14134","title":"Developing and Evaluating Tiny to Medium-Sized Turkish BERT Models","created":"2023-07-26","cited_by_count":8,"area":null},{"id":"2201.08539","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","created":"2022-01-21","cited_by_count":7,"area":null},{"id":"2311.00867","title":"Automatic Disfluency Detection from Untranscribed Speech","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2103.06418","title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2104.12847","title":"Morph Call: Probing Morphosyntactic Content of Multilingual Transformers","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2207.01012","title":"Mental Illness Classification on Social Media Texts using Deep Learning and Transfer Learning","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2103.00573","title":"RuSentEval: Linguistic Source, Encoder Force!","created":"2021-02-28","cited_by_count":4,"area":null},{"id":"2210.09840","title":"Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging","created":"2022-10-18","cited_by_count":4,"area":null},{"id":"2304.11520","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","created":"2023-04-23","cited_by_count":2,"area":null},{"id":"2107.04512","title":"Using Machine Translation to Localize Task Oriented NLG Output","created":"2021-07-09","cited_by_count":1,"area":null},{"id":"2109.08449","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2305.05834","title":"Unsupervised Dense Retrieval Training with Web Anchors","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2103.00728","title":"BERT-based knowledge extraction method of unstructured domain text","created":"2021-03-01","cited_by_count":0,"area":null},{"id":"2104.06591","title":"Zero-Resource Multi-Dialectal Arabic Natural Language Understanding","created":"2021-04-14","cited_by_count":0,"area":null},{"id":"2104.14314","title":"MOROCCO: Model Resource Comparison Framework","created":"2021-04-29","cited_by_count":0,"area":null},{"id":"2106.07137","title":"Why Can You Lay Off Heads? Investigating How BERT Heads Transfer","created":"2021-06-14","cited_by_count":0,"area":null},{"id":"2109.08627","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2311.17267","title":"E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2403.14840","title":"TAMS: Translation-Assisted Morphological Segmentation","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2508.08635","title":"Classifier Language Models: Unifying Sparse Finetuning and Adaptive Tokenization for Specialized Classification Tasks","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2605.25463","title":"A Lightweight Hybrid Transformer-CRF Architecture for Multi-Type Bangla Medical Entity Recognition","created":"2026-05-25","cited_by_count":0,"area":null}],"next_cursor":null}