{"total":41,"rows":[{"id":"2305.13820","title":"An Open Dataset and Model for Language Identification","created":"2023-05-23","cited_by_count":50,"area":null},{"id":"2401.05632","title":"Natural Language Processing for Dialects of a Language: A Survey","created":"2024-01-11","cited_by_count":40,"area":null},{"id":"2210.11744","title":"AfroLID: A Neural Language Identification Tool for African Languages","created":"2022-10-21","cited_by_count":39,"area":null},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"area":null},{"id":"2105.15071","title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2305.20080","title":"Findings of the VarDial Evaluation Campaign 2023","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2303.01490","title":"Language Variety Identification with True Labels","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2103.05552","title":"Comparing Approaches to Dravidian Language Identification","created":"2021-03-09","cited_by_count":11,"area":null},{"id":"2406.06263","title":"MaskLID: Code-Switching Language Identification through Iterative Masking","created":"2024-06-10","cited_by_count":11,"area":null},{"id":"2402.17467","title":"Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2304.01322","title":"PALI: A Language Identification Benchmark for Perso-Arabic Scripts","created":"2023-04-03","cited_by_count":7,"area":null},{"id":"2202.12163","title":"Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2305.14263","title":"LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2311.09696","title":"Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2602.13139","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2102.06282","title":"A reproduction of Apple's bi-directional LSTM models for language identification in short strings","created":"2021-02-11","cited_by_count":4,"area":null},{"id":"2206.04327","title":"Language Identification for Austronesian Languages","created":"2022-06-09","cited_by_count":3,"area":null},{"id":"2402.01505","title":"Code-Switched Language Identification is Harder Than You Think","created":"2024-02-02","cited_by_count":3,"area":null},{"id":"2402.17914","title":"Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2509.17768","title":"DIVERS-Bench: Evaluating Language Identification Across Domain Shifts and Code-Switching","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2111.05097","title":"Cross-Lingual Citations in English Papers: A Large-Scale Analysis of Prevalence, Usage, and Impact","created":"2021-11-07","cited_by_count":2,"area":null},{"id":"2401.06513","title":"ML-On-Rails: Safeguarding Machine Learning Models in Software Systems A Case Study","created":"2024-01-12","cited_by_count":2,"area":null},{"id":"2502.06692","title":"Multi-label Scandinavian Language Identification (SLIDE)","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2602.17655","title":"What Language is This? Ask Your Tokenizer","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2401.14569","title":"Detecting Structured Language Alternations in Historical Documents by Combining Language Identification with Fourier Analysis","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2404.18510","title":"Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2408.04554","title":"Moly\\'e: A Corpus-based Approach to Language Contact in Colonial France","created":"2024-08-08","cited_by_count":1,"area":null},{"id":"2504.21540","title":"Improving Informally Romanized Language Identification","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2109.09862","title":"Language Identification with a Reciprocal Rank Classifier","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2203.04831","title":"Automatic Language Identification for Celtic Texts","created":"2022-03-09","cited_by_count":0,"area":null},{"id":"2211.05031","title":"Improving Performance of Automatic Keyword Extraction (AKE) Methods Using PoS-Tagging and Enhanced Semantic-Awareness","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2406.17901","title":"Script-Agnostic Language Identification","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2512.08143","title":"PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.28418","title":"LombardoGraphia: Automatic Classification of Lombard Orthography Variants","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2606.06088","title":"CHALIS: A Challenge Dataset for Language Identification in Difficult Scenarios","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.18597","title":"Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.00581","title":"Loanword or Switch? The Annotation Boundary, Not the Model, Drives Kazakh-Russian Code-Switching Identification","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.05099","title":"Improving Language Identification for Code-Switched Utterances with Integer Linear Programming","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.16601","title":"MixLID: Token-Level Language Identification in Mixed-Language Text","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}