{"total":49,"rows":[{"id":"2405.10138","title":"PL-MTEB: Polish Massive Text Embedding Benchmark","created":"2024-05-16","cited_by_count":19,"area":null},{"id":"2305.19840","title":"BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2402.13350","title":"PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods","created":"2024-02-20","cited_by_count":14,"area":null},{"id":"2205.08808","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","created":"2022-05-18","cited_by_count":13,"area":null},{"id":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2207.12759","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","created":"2022-07-26","cited_by_count":11,"area":null},{"id":"2305.05486","title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset","created":"2023-05-09","cited_by_count":11,"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":"2212.08897","title":"PolQA: Polish Question Answering Dataset","created":"2022-12-17","cited_by_count":7,"area":null},{"id":"2408.15040","title":"A Survey of Large Language Models for European Languages","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2411.15734","title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","created":"2024-11-24","cited_by_count":6,"area":null},{"id":"2309.08469","title":"Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2209.12516","title":"End-to-end Multilingual Coreference Resolution with Mention Head Prediction","created":"2022-09-26","cited_by_count":4,"area":null},{"id":"2408.16893","title":"Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUD","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2501.02631","title":"Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian","created":"2025-01-05","cited_by_count":3,"area":null},{"id":"2109.05361","title":"COMBO: State-of-the-Art Morphosyntactic Analysis","created":"2021-09-11","cited_by_count":2,"area":null},{"id":"2305.05474","title":"Going beyond research datasets: Novel intent discovery in the industry setting","created":"2023-05-09","cited_by_count":2,"area":null},{"id":"2312.08198","title":"Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2506.07645","title":"Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2506.16322","title":"PL-Guard: Benchmarking Language Model Safety for Polish","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2107.03809","title":"COMBO: a new module for EUD parsing","created":"2021-07-08","cited_by_count":1,"area":null},{"id":"2108.10580","title":"Detection of Criminal Texts for the Polish State Border Guard","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2308.03103","title":"Improving Domain-Specific Retrieval by NLI Fine-Tuning","created":"2023-08-06","cited_by_count":1,"area":null},{"id":"2312.07599","title":"Contrastive News and Social Media Linking using BERT for Articles and Tweets across Dual Platforms","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2403.16968","title":"Evaluating Shortest Edit Script Methods for Contextual Lemmatization","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2407.01393","title":"POLygraph: Polish Fake News Dataset","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2408.02337","title":"Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2411.03779","title":"Multilingual hierarchical classification of job advertisements for job vacancy statistics","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2412.17533","title":"Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2511.03830","title":"Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2603.12191","title":"Long-Context Encoder Models for Polish Language Understanding","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.13436","title":"Pretraining Language Models with Subword Regularization: An Empirical Study of BPE Dropout in Low-Resource NLP","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2111.13982","title":"Language models in word sense disambiguation for Polish","created":"2021-11-27","cited_by_count":0,"area":null},{"id":"2201.03521","title":"Polish Natural Language Inference and Factivity -- an Expert-based Dataset and Benchmarks","created":"2022-01-10","cited_by_count":0,"area":null},{"id":"2207.07586","title":"Does Twitter know your political views? POLiTweets dataset and semi-automatic method for political leaning discovery","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2209.11016","title":"Approaching English-Polish Machine Translation Quality Assessment with Neural-based Methods","created":"2022-09-22","cited_by_count":0,"area":null},{"id":"2304.05336","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2310.14325","title":"Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2402.14408","title":"Transferring BERT Capabilities from High-Resource to Low-Resource Languages Using Vocabulary Matching","created":"2024-02-22","cited_by_count":0,"area":null},{"id":"2403.04507","title":"NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems","created":"2024-03-07","cited_by_count":0,"area":null},{"id":"2410.04620","title":"Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2410.04621","title":"Punctuation Prediction for Polish Texts using Transformers","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2502.17664","title":"Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2502.20046","title":"Polish-ASTE: Aspect-Sentiment Triplet Extraction Datasets for Polish","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.06062","title":"Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2505.19254","title":"Unveiling Dual Quality in Product Reviews: An NLP-Based Approach","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2601.09722","title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2609.01379","title":"Polish ModernBERT: The Long and Short of Polish Language Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.29266","title":"Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}