{"total":102,"rows":[{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"area":null},{"id":"2106.12672","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","created":"2021-06-23","cited_by_count":160,"area":null},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"area":null},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2211.09102","title":"Prompting PaLM for Translation: Assessing Strategies and Performance","created":"2022-11-16","cited_by_count":145,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104,"area":null},{"id":"2110.06341","title":"Learning Compact Metrics for MT","created":"2021-10-12","cited_by_count":93,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49,"area":null},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48,"area":null},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40,"area":null},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2311.08849","title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining","created":"2023-11-15","cited_by_count":37,"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":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2309.11285","title":"Overview of AuTexTification at IberLEF 2023: Detection and Attribution of Machine-Generated Text in Multiple Domains","created":"2023-09-20","cited_by_count":31,"area":null},{"id":"2405.07883","title":"Zero-Shot Tokenizer Transfer","created":"2024-05-13","cited_by_count":31,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2212.10180","title":"IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages","created":"2022-12-20","cited_by_count":27,"area":null},{"id":"2309.10931","title":"A Family of Pretrained Transformer Language Models for Russian","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2406.19232","title":"RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2305.13989","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2109.07306","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training","created":"2021-09-15","cited_by_count":22,"area":null},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2108.11696","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","created":"2021-08-26","cited_by_count":18,"area":null},{"id":"2109.04727","title":"A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations","created":"2021-09-10","cited_by_count":17,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2109.07348","title":"Cross-lingual Transfer of Monolingual Models","created":"2021-09-15","cited_by_count":14,"area":null},{"id":"2201.12501","title":"Does Transliteration Help Multilingual Language Modeling?","created":"2022-01-29","cited_by_count":14,"area":null},{"id":"2211.00922","title":"Dialect-robust Evaluation of Generated Text","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2305.12092","title":"ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain","created":"2023-05-20","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":"2205.01381","title":"Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer Learning","created":"2022-05-03","cited_by_count":13,"area":null},{"id":"2209.07841","title":"Findings of the Shared Task on Multilingual Coreference Resolution","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2205.06356","title":"Beyond Static Models and Test Sets: Benchmarking the Potential of Pre-trained Models Across Tasks and Languages","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2410.05183","title":"Beyond Correlation: Interpretable Evaluation of Machine Translation Metrics","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2204.06546","title":"Disentangling Uncertainty in Machine Translation Evaluation","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2212.09305","title":"SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2402.01535","title":"An Empirical Analysis of Diversity in Argument Summarization","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2209.07278","title":"\\'UFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2105.04201","title":"REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2210.07904","title":"HashFormers: Towards Vocabulary-independent Pre-trained Transformers","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2306.01709","title":"Distilling Efficient Language-Specific Models for Cross-Lingual Transfer","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2406.01468","title":"Understanding Token Probability Encoding in Output Embeddings","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2411.00390","title":"MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration","created":"2024-11-01","cited_by_count":6,"area":null},{"id":"2403.19335","title":"KazSAnDRA: Kazakh Sentiment Analysis Dataset of Reviews and Attitudes","created":"2024-03-28","cited_by_count":5,"area":null},{"id":"2201.00598","title":"Toxicity Detection for Indic Multilingual Social Media Content","created":"2022-01-03","cited_by_count":4,"area":null},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2403.12666","title":"Multi-Dimensional Machine Translation Evaluation: Model Evaluation and Resource for Korean","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2412.08341","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","created":"2024-12-11","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":"2505.20624","title":"POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2305.17679","title":"RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts","created":"2023-05-28","cited_by_count":3,"area":null},{"id":"2309.10299","title":"Using fine-tuning and min lookahead beam search to improve Whisper","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2603.26663","title":"Weight Tying Biases Token Embeddings Towards the Output Space","created":"2026-03-27","cited_by_count":3,"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":"2306.02130","title":"Extending an Event-type Ontology: Adding Verbs and Classes Using Fine-tuned LLMs Suggestions","created":"2023-06-03","cited_by_count":2,"area":null},{"id":"2501.11914","title":"LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2501.11918","title":"LuxVeri at GenAI Detection Task 3: Cross-Domain Detection of AI-Generated Text Using Inverse Perplexity-Weighted Ensemble of Fine-Tuned Transformer Models","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2305.02607","title":"DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2308.08688","title":"Lightweight Adaptation of Neural Language Models via Subspace Embedding","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2308.15793","title":"HAlf-MAsked Model for Named Entity Sentiment analysis","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2311.06379","title":"DeMuX: Data-efficient Multilingual Learning","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2401.07847","title":"Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2410.15051","title":"Automatic identification of diagnosis from hospital discharge letters via weakly supervised Natural Language Processing","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2503.18253","title":"Enhancing Multi-Label Emotion Analysis and Corresponding Intensities for Ethiopian Languages","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2512.23065","title":"TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2208.10751","title":"Predicting Query-Item Relationship using Adversarial Training and Robust Modeling Techniques","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2209.03851","title":"5q032e@SMM4H'22: Transformer-based classification of premise in tweets related to COVID-19","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2211.12677","title":"Word-Level Representation From Bytes For Language Modeling","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2301.00422","title":"Leveraging Semantic Representations Combined with Contextual Word Representations for Recognizing Textual Entailment in Vietnamese","created":"2023-01-01","cited_by_count":0,"area":null},{"id":"2302.07010","title":"Enhancing Model Performance in Multilingual Information Retrieval with Comprehensive Data Engineering Techniques","created":"2023-02-14","cited_by_count":0,"area":null},{"id":"2303.01794","title":"Hitachi at SemEval-2023 Task 3: Exploring Cross-lingual Multi-task Strategies for Genre and Framing Detection in Online News","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2305.02300","title":"Evaluating the Efficacy of Length-Controllable Machine Translation","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2401.09343","title":"Efficient slot labelling","created":"2024-01-17","cited_by_count":0,"area":null},{"id":"2506.08174","title":"LLM-BT-Terms: Back-Translation as a Framework for Terminology Standardization and Dynamic Semantic Embedding","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2509.10737","title":"PolyTruth: Multilingual Disinformation Detection using Transformer-Based Language Models","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.00323","title":"Comparative Analysis of 47 Context-Based Question Answer Models Across 8 Diverse Datasets","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.06347","title":"What Matters When Building Universal Multilingual Named Entity Recognition Models?","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2605.02608","title":"Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.21718","title":"Leveraging LaBSE with Progressive Curriculum Learning for Multicultural Polarization","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.08362","title":"Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.22699","title":"Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.25202","title":"A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":"100"}