{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/dialect-identification","name":"Dialect Identification","slug":"dialect-identification","description_markdown":"Dialectal Arabic Identification","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":189,"papers_with_code":33,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/arsarcasm-v2","name":"ArSarcasm-v2","full_name":"","num_papers_in_archive":15},{"url":"/dataset/arsarcasm","name":"ArSarcasm","full_name":"","num_papers_in_archive":14},{"url":"/dataset/frecdo","name":"FreCDo","full_name":"French cross-domain","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/language-identification","name":"Language Identification"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":189,"of_with_code":33,"tagged_in_all":189,"counts":{"archive_papers_tagged":189,"with_a_code_link":33,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":189,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/glotlid-language-identification-for-low","slug":"glotlid-language-identification-for-low","title":"GlotLID: Language Identification for Low-Resource Languages","date":"2023-10-24","arxiv_id":"2310.16248","repositories_listed":3,"syntology":null},{"url":"/paper/resource-aware-arabic-llm-creation-model","slug":"resource-aware-arabic-llm-creation-model","title":"Resource-Aware Arabic LLM Creation: Model Adaptation, Integration, and Multi-Domain Testing","date":"2024-12-23","arxiv_id":"2412.17548","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dialect-vietnamese-task-dataset","slug":"multi-dialect-vietnamese-task-dataset","title":"Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges","date":"2024-10-04","arxiv_id":"2410.03458","repositories_listed":1,"syntology":null},{"url":"/paper/sebastian-basti-wastl-recognizing-named","slug":"sebastian-basti-wastl-recognizing-named","title":"Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data","date":"2024-03-19","arxiv_id":"2403.12749","repositories_listed":1,"syntology":null},{"url":"/paper/artst-arabic-text-and-speech-transformer","slug":"artst-arabic-text-and-speech-transformer","title":"ArTST: Arabic Text and Speech Transformer","date":"2023-10-25","arxiv_id":"2310.16621","repositories_listed":1,"syntology":null},{"url":"/paper/aldi-quantifying-the-arabic-level-of","slug":"aldi-quantifying-the-arabic-level-of","title":"ALDi: Quantifying the Arabic Level of Dialectness of Text","date":"2023-10-20","arxiv_id":"2310.13747","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-dialect-identification-under-scrutiny","slug":"arabic-dialect-identification-under-scrutiny","title":"Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification","date":"2023-10-20","arxiv_id":"2310.13661","repositories_listed":1,"syntology":null},{"url":"/paper/dada-dialect-adaptation-via-dynamic","slug":"dada-dialect-adaptation-via-dynamic","title":"DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules","date":"2023-05-22","arxiv_id":"2305.13406","repositories_listed":1,"syntology":null},{"url":"/paper/north-sami-dialect-identification-with-self","slug":"north-sami-dialect-identification-with-self","title":"North Sámi Dialect Identification with Self-supervised Speech Models","date":"2023-05-19","arxiv_id":"2305.11864","repositories_listed":1,"syntology":null},{"url":"/paper/a-parameter-efficient-learning-approach-to","slug":"a-parameter-efficient-learning-approach-to","title":"A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model","date":"2023-05-18","arxiv_id":"2305.11244","repositories_listed":1,"syntology":null},{"url":"/paper/two-stage-pipeline-for-multilingual-dialect","slug":"two-stage-pipeline-for-multilingual-dialect","title":"Two-stage Pipeline for Multilingual Dialect Detection","date":"2023-03-06","arxiv_id":"2303.03487","repositories_listed":1,"syntology":null},{"url":"/paper/frecdo-a-large-corpus-for-french-cross-domain","slug":"frecdo-a-large-corpus-for-french-cross-domain","title":"FreCDo: A Large Corpus for French Cross-Domain Dialect Identification","date":"2022-12-15","arxiv_id":"2212.07707","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-study-of-contrastive-learning-for","slug":"a-benchmark-study-of-contrastive-learning-for","title":"A Benchmark Study of Contrastive Learning for Arabic Social Meaning","date":"2022-10-22","arxiv_id":"2210.12314","repositories_listed":1,"syntology":null},{"url":"/paper/nadi-2022-the-third-nuanced-arabic-dialect","slug":"nadi-2022-the-third-nuanced-arabic-dialect","title":"NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task","date":"2022-10-18","arxiv_id":"2210.09582","repositories_listed":1,"syntology":null},{"url":"/paper/findings-of-the-vardial-evaluation-campaign-2","slug":"findings-of-the-vardial-evaluation-campaign-2","title":"Findings of the VarDial Evaluation Campaign 2022","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/italian-language-and-dialect-identification","slug":"italian-language-and-dialect-identification","title":"Italian Language and Dialect Identification and Regional French Variety Detection using Adaptive Naive Bayes","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distilling-the-knowledge-of-romanian-berts","slug":"distilling-the-knowledge-of-romanian-berts","title":"Distilling the Knowledge of Romanian BERTs Using Multiple Teachers","date":"2021-12-23","arxiv_id":"2112.12650","repositories_listed":1,"syntology":null},{"url":"/paper/finnish-dialect-identification-the-effect-of-1","slug":"finnish-dialect-identification-the-effect-of-1","title":"Finnish Dialect Identification: The Effect of Audio and Text","date":"2021-11-06","arxiv_id":"2111.03800","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-multi-scale-convolution-for-dialect","slug":"dynamic-multi-scale-convolution-for-dialect","title":"Dynamic Multi-scale Convolution for Dialect Identification","date":"2021-08-02","arxiv_id":"2108.07787","repositories_listed":1,"syntology":null},{"url":"/paper/aracovid19-mfh-arabic-covid-19-multi-label","slug":"aracovid19-mfh-arabic-covid-19-multi-label","title":"AraCOVID19-MFH: Arabic COVID-19 Multi-label Fake News and Hate Speech Detection Dataset","date":"2021-05-07","arxiv_id":"2105.03143","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-the-performance-of-cnns-and-shallow","slug":"comparing-the-performance-of-cnns-and-shallow","title":"Comparing the Performance of CNNs and Shallow Models for Language Identification","date":"2021-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nadi-2021-the-second-nuanced-arabic-dialect","slug":"nadi-2021-the-second-nuanced-arabic-dialect","title":"NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task","date":"2021-03-04","arxiv_id":"2103.08466","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-marbert-for-improved-arabic-dialect","slug":"adapting-marbert-for-improved-arabic-dialect","title":"Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task","date":"2021-03-01","arxiv_id":"2103.01065","repositories_listed":1,"syntology":null},{"url":"/paper/a-dual-encoding-system-for-dialect","slug":"a-dual-encoding-system-for-dialect","title":"A dual-encoding system for dialect classification","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/arabic-dialect-identification-using-bert-fine","slug":"arabic-dialect-identification-using-bert-fine","title":"Arabic Dialect Identification Using BERT Fine-Tuning","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/toward-micro-dialect-identification-in","slug":"toward-micro-dialect-identification-in","title":"Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments","date":"2020-10-10","arxiv_id":"2010.04900","repositories_listed":1,"syntology":null},{"url":"/paper/the-unreasonable-effectiveness-of-machine","slug":"the-unreasonable-effectiveness-of-machine","title":"The Unreasonable Effectiveness of Machine Learning in Moldavian versus Romanian Dialect Identification","date":"2020-07-30","arxiv_id":"2007.15700","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dialect-arabic-bert-for-country-level","slug":"multi-dialect-arabic-bert-for-country-level","title":"Multi-Dialect Arabic BERT for Country-Level Dialect Identification","date":"2020-07-10","arxiv_id":"2007.05612","repositories_listed":1,"syntology":null},{"url":"/paper/camel-tools-an-open-source-python-toolkit-for","slug":"camel-tools-an-open-source-python-toolkit-for","title":"CAMeL Tools: An Open Source Python Toolkit for Arabic Natural Language Processing","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/speech-recognition-challenge-in-the-wild","slug":"speech-recognition-challenge-in-the-wild","title":"Speech Recognition Challenge in the Wild: Arabic MGB-3","date":"2017-09-21","arxiv_id":"1709.07276","repositories_listed":1,"syntology":null},{"url":"/paper/a-character-level-convolutional-neural","slug":"a-character-level-convolutional-neural","title":"A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects","date":"2016-09-24","arxiv_id":"1609.07568","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-unsupervised-dutch-word-embeddings","slug":"evaluating-unsupervised-dutch-word-embeddings","title":"Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource","date":"2016-07-01","arxiv_id":"1607.00225","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-dialect-detection-in-arabic","slug":"automatic-dialect-detection-in-arabic","title":"Automatic Dialect Detection in Arabic Broadcast Speech","date":"2015-09-23","arxiv_id":"1509.06928","repositories_listed":1,"syntology":null},{"url":null,"slug":"voice-conversion-improves-cross-domain","title":"Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification","date":"2025-05-30","arxiv_id":"2505.24713","repositories_listed":0,"syntology":null},{"url":null,"slug":"hitz-at-vardial-2025-norsid-overcoming-data","title":"HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation","date":"2024-12-13","arxiv_id":"2412.10095","repositories_listed":0,"syntology":null},{"url":null,"slug":"aradice-benchmarks-for-dialectal-and-cultural","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","date":"2024-09-17","arxiv_id":"2409.11404","repositories_listed":0,"syntology":null},{"url":null,"slug":"literary-and-colloquial-dialect","title":"Literary and Colloquial Dialect Identification for Tamil using Acoustic Features","date":"2024-08-27","arxiv_id":"2408.14887","repositories_listed":0,"syntology":null},{"url":null,"slug":"literary-and-colloquial-tamil-dialect","title":"Literary and Colloquial Tamil Dialect Identification","date":"2024-08-25","arxiv_id":"2408.13739","repositories_listed":0,"syntology":null},{"url":null,"slug":"dznlp-at-nadi-2024-shared-task-multi","title":"dzNLP at NADI 2024 Shared Task: Multi-Classifier Ensemble with Weighted Voting and TF-IDF Features","date":"2024-07-18","arxiv_id":"2407.13608","repositories_listed":0,"syntology":null},{"url":null,"slug":"nadi-2024-the-fifth-nuanced-arabic-dialect","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","date":"2024-07-06","arxiv_id":"2407.04910","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-dialect-identification-in","title":"Exploiting Dialect Identification in Automatic Dialectal Text Normalization","date":"2024-07-03","arxiv_id":"2407.03020","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-energy-based-models-for-out-of","title":"Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification","date":"2024-06-26","arxiv_id":"2406.18067","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-text-to-speech-for-arabic","title":"Towards Zero-Shot Text-To-Speech for Arabic Dialects","date":"2024-06-24","arxiv_id":"2406.16751","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-speech-recognition-and-dialect","title":"Low-resource speech recognition and dialect identification of Irish in a multi-task framework","date":"2024-05-02","arxiv_id":"2405.01293","repositories_listed":0,"syntology":null},{"url":null,"slug":"usthb-at-nadi-2023-shared-task-exploring","title":"USTHB at NADI 2023 shared task: Exploring Preprocessing and Feature Engineering Strategies for Arabic Dialect Identification","date":"2023-12-16","arxiv_id":"2312.10536","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-adaptive-pre-training-of","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","date":"2023-12-12","arxiv_id":"2312.07338","repositories_listed":0,"syntology":null},{"url":null,"slug":"mavericks-at-nadi-2023-shared-task","title":"Mavericks at NADI 2023 Shared Task: Unravelling Regional Nuances through Dialect Identification using Transformer-based Approach","date":"2023-11-30","arxiv_id":"2311.18739","repositories_listed":0,"syntology":null},{"url":null,"slug":"nadi-2023-the-fourth-nuanced-arabic-dialect","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","date":"2023-10-24","arxiv_id":"2310.16117","repositories_listed":0,"syntology":null},{"url":null,"slug":"yet-another-model-for-arabic-dialect","title":"Yet Another Model for Arabic Dialect Identification","date":"2023-10-20","arxiv_id":"2310.13812","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-accent-dialect-identification-and","title":"Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognition","date":"2023-10-17","arxiv_id":"2310.11004","repositories_listed":0,"syntology":null},{"url":null,"slug":"voxarabica-a-robust-dialect-aware-arabic","title":"VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System","date":"2023-10-17","arxiv_id":"2310.11069","repositories_listed":0,"syntology":null},{"url":null,"slug":"rodia-a-new-dataset-for-romanian-dialect","title":"RoDia: A New Dataset for Romanian Dialect Identification from Speech","date":"2023-09-06","arxiv_id":"2309.03378","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-out-of-distribution-dialect","title":"Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance","date":"2023-08-09","arxiv_id":"2308.04886","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-spoken-dialect-identification-of","title":"Towards spoken dialect identification of Irish","date":"2023-07-14","arxiv_id":"2307.07436","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-robustness-of-arabic-speech-dialect","title":"On the Robustness of Arabic Speech Dialect Identification","date":"2023-06-01","arxiv_id":"2306.03789","repositories_listed":0,"syntology":null},{"url":null,"slug":"stt4sg-350-a-speech-corpus-for-all-swiss","title":"STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions","date":"2023-05-30","arxiv_id":"2305.18855","repositories_listed":0,"syntology":null},{"url":null,"slug":"saids-a-novel-approach-for-sentiment-analysis","title":"SAIDS: A Novel Approach for Sentiment Analysis Informed of Dialect and Sarcasm","date":"2023-01-06","arxiv_id":"2301.02521","repositories_listed":0,"syntology":null},{"url":null,"slug":"camelira-an-arabic-multi-dialect","title":"Camelira: An Arabic Multi-Dialect Morphological Disambiguator","date":"2022-11-30","arxiv_id":"2211.16807","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-improves-french-cross","title":"Transfer Learning Improves French Cross-Domain Dialect Identification: NRC @ VarDial 2022","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dialects-identification-of-armenian-language","title":"Dialects Identification of Armenian Language","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"german-dialect-identification-and-mapping-for","title":"German Dialect Identification and Mapping for Preservation and Recovery","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-aggregation-of-dialectal-data","title":"Hierarchical Aggregation of Dialectal Data for Arabic Dialect Identification","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-models-or-feature-engineering-the","title":"Pre-trained Models or Feature Engineering: The Case of Dialectal Arabic","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"early-guessing-for-dialect-identification","title":"Early Guessing for Dialect Identification","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tunbert-pretrained-contextualized-text","title":"TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect","date":"2021-11-25","arxiv_id":"2111.13138","repositories_listed":0,"syntology":null},{"url":null,"slug":"qasr-qcri-aljazeera-speech-resource-a-large-1","title":"QASR: QCRI Aljazeera Speech Resource A Large Scale Annotated Arabic Speech Corpus","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vowel-based-meeteilon-dialect-identification","title":"Vowel-based Meeteilon dialect identification using a Random Forest classifier","date":"2021-07-26","arxiv_id":"2107.13419","repositories_listed":0,"syntology":null},{"url":null,"slug":"oriental-language-recognition-olr-2020","title":"Oriental Language Recognition (OLR) 2020: Summary and Analysis","date":"2021-07-05","arxiv_id":"2107.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-end-to-end-speech-models-learn-about","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","date":"2021-07-01","arxiv_id":"2107.00439","repositories_listed":0,"syntology":null},{"url":null,"slug":"qasr-qcri-aljazeera-speech-resource-a-large","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","date":"2021-06-24","arxiv_id":"2106.13000","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-dialect-identification-based-on-a","title":"Arabic Dialect Identification based on a Weighted Concatenation of TF-IDF Features","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"country-level-arabic-dialect-identification","title":"Country-level Arabic Dialect Identification Using Small Datasets with Integrated Machine Learning Techniques and Deep Learning Models","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"country-level-arabic-dialect-identification-1","title":"Country-level Arabic Dialect Identification using RNNs with and without Linguistic Features","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-identification-through-adversarial","title":"Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-vardial-evaluation-campaign-1","title":"Findings of the VarDial Evaluation Campaign 2021","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-based-approach-for-arabic","title":"Machine Learning-Based Approach for Arabic Dialect Identification","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"naive-bayes-based-experiments-in-romanian","title":"Naive Bayes-based Experiments in Romanian Dialect Identification","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"qadi-arabic-dialect-identification-in-the","title":"QADI: Arabic Dialect Identification in the Wild","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ul2c-mapping-user-locations-to-countries-on","title":"UL2C: Mapping User Locations to Countries on Arabic Twitter","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-approaches-to-dravidian-language","title":"Comparing Approaches to Dravidian Language Identification","date":"2021-03-09","arxiv_id":"2103.05552","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-identification-in-nuanced-arabic","title":"Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT","date":"2021-02-19","arxiv_id":"2102.09749","repositories_listed":0,"syntology":null},{"url":null,"slug":"unibuckernel-geolocating-swiss-german-jodels","title":"UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning","date":"2021-02-18","arxiv_id":"2102.09379","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-report-on-the-vardial-evaluation-campaign","title":"A Report on the VarDial Evaluation Campaign 2020","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-multilingual-and-monolingual","title":"Applying Multilingual and Monolingual Transformer-Based Models for Dialect Identification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-dialect-identification-an-arabic-bert","title":"Arabic dialect identification: An Arabic-BERT model with data augmentation and ensembling strategy","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-between-voting-classifier-and-deep","title":"Comparison between Voting Classifier and Deep Learning methods for Arabic Dialect Identification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-identification-under-domain-shift","title":"Dialect Identification under Domain Shift: Experiments with Discriminating Romanian and Moldavian","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experiments-in-language-variety-geolocation","title":"Experiments in Language Variety Geolocation and Dialect Identification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-power-of-romanian-bert-for","title":"Exploring the Power of Romanian BERT for Dialect Identification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"faheem-at-nadi-shared-task-identifying-the","title":"Faheem at NADI shared task: Identifying the dialect of Arabic tweet","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-nuanced-dialect-for-arabic-tweets","title":"Identifying Nuanced Dialect for Arabic Tweets with Deep Learning and Reverse Translation Corpus Extension System","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ltg-st-at-nadi-shared-task-1-arabic-dialect","title":"LTG-ST at NADI Shared Task 1: Arabic Dialect Identification using a Stacking Classifier","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-vs-oversampling-based-classification","title":"Simple vs Oversampling-based Classification Methods for Fine Grained Arabic Dialect Identification in Twitter","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-qmul-hrbdt-contribution-to-the-nadi","title":"The QMUL/HRBDT contribution to the NADI Arabic Dialect Identification Shared Task","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-deep-language-and-dialect","title":"Unsupervised Deep Language and Dialect Identification for Short Texts","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-combination-of-bert-and-n-gram","title":"Weighted combination of BERT and N-GRAM features for Nuanced Arabic Dialect Identification","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-dialect-identification-using-bert","title":"Arabic Dialect Identification Using BERT-Based Domain Adaptation","date":"2020-11-13","arxiv_id":"2011.06977","repositories_listed":0,"syntology":null},{"url":null,"slug":"nadi-2020-the-first-nuanced-arabic-dialect","title":"NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task","date":"2020-10-21","arxiv_id":"2010.11334","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-deep-learning-and-string-kernels","title":"Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets","date":"2020-10-07","arxiv_id":"2010.03614","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-arabic-dialect-identification","title":"Automatic Arabic Dialect Identification Systems for Written Texts: A Survey","date":"2020-09-26","arxiv_id":"2009.12622","repositories_listed":0,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/dialect-identification/papers/2","json":"/task/dialect-identification/papers/2.json","rows":89}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"34941b491a80283c4b97bc10200d562c007aeca2737d0f5944debd0d2d5e3017","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}