{"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/xlm-r/papers/2","list_of":"/task/xlm-r","task":"XLM-R","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":221,"counts":{"archive_papers_tagged":221,"with_a_code_link":99,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":221,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"first_page":"/task/xlm-r","prev":"/task/xlm-r","next":"/task/xlm-r/papers/3","papers":[{"url":null,"slug":"subasa-adapting-language-models-for-low","title":"Subasa -- Adapting Language Models for Low-resourced Offensive Language Detection in Sinhala","date":"2025-04-02","arxiv_id":"2504.02178","repositories_listed":0,"syntology":null},{"url":null,"slug":"amasquad-a-benchmark-for-amharic-extractive","title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering","date":"2025-02-04","arxiv_id":"2502.02047","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-effectiveness-of-xai","title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","date":"2025-01-26","arxiv_id":"2501.15374","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-approaches-to-sentiment-analysis","title":"Comparative Approaches to Sentiment Analysis Using Datasets in Major European and Arabic Languages","date":"2025-01-21","arxiv_id":"2501.12540","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuocchuvip123-at-comedi-shared-task","title":"FuocChuVIP123 at CoMeDi Shared Task: Disagreement Ranking with XLM-Roberta Sentence Embeddings and Deep Neural Regression","date":"2025-01-21","arxiv_id":"2501.12336","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-training-of-bilingual-islamic-llm","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","date":"2025-01-17","arxiv_id":"2501.10175","repositories_listed":0,"syntology":null},{"url":null,"slug":"babylms-for-isixhosa-data-efficient-language","title":"BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context","date":"2025-01-07","arxiv_id":"2501.03855","repositories_listed":0,"syntology":null},{"url":null,"slug":"ustcctsu-at-semeval-2024-task-1-reducing","title":"USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task","date":"2024-11-28","arxiv_id":"2411.18990","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrofitting-large-language-models-with","title":"Retrofitting Large Language Models with Dynamic Tokenization","date":"2024-11-27","arxiv_id":"2411.18553","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-contextualized-language","title":"Transformer-Based Contextualized Language Models Joint with Neural Networks for Natural Language Inference in Vietnamese","date":"2024-11-20","arxiv_id":"2411.13407","repositories_listed":0,"syntology":null},{"url":"/paper/mgte-generalized-long-context-text","slug":"mgte-generalized-long-context-text","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","date":"2024-07-29","arxiv_id":"2407.19669","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mgte-generalized-long-context-text#ran","syntology_url":"https://syntology.ai/paper/2407.19669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19669"}},"official":null}},{"url":null,"slug":"the-model-arena-for-cross-lingual-sentiment","title":"The Model Arena for Cross-lingual Sentiment Analysis: A Comparative Study in the Era of Large Language Models","date":"2024-06-27","arxiv_id":"2406.19358","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-large-language-models-and-curse","title":"Multilingual Large Language Models and Curse of Multilinguality","date":"2024-06-15","arxiv_id":"2406.10602","repositories_listed":0,"syntology":null},{"url":null,"slug":"targeted-multilingual-adaptation-for-low","title":"Targeted Multilingual Adaptation for Low-resource Language Families","date":"2024-05-20","arxiv_id":"2405.12413","repositories_listed":0,"syntology":null},{"url":null,"slug":"software-mention-recognition-with-a-three","title":"Software Mention Recognition with a Three-Stage Framework Based on BERTology Models at SOMD 2024","date":"2024-04-23","arxiv_id":"2405.01575","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-mental-health-prediction-tasks-for","title":"Adapting Mental Health Prediction Tasks for Cross-lingual Learning via Meta-Training and In-context Learning with Large Language Model","date":"2024-04-13","arxiv_id":"2404.09045","repositories_listed":0,"syntology":null},{"url":null,"slug":"mainlp-at-semeval-2024-task-1-analyzing","title":"MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness","date":"2024-04-03","arxiv_id":"2404.02570","repositories_listed":0,"syntology":null},{"url":null,"slug":"solution-for-emotion-prediction-competition","title":"Solution for Emotion Prediction Competition of Workshop on Emotionally and Culturally Intelligent AI","date":"2024-03-26","arxiv_id":"2403.17683","repositories_listed":0,"syntology":null},{"url":null,"slug":"machines-do-see-color-a-guideline-to-classify","title":"Machines Do See Color: A Guideline to Classify Different Forms of Racist Discourse in Large Corpora","date":"2024-01-17","arxiv_id":"2401.09333","repositories_listed":0,"syntology":null},{"url":null,"slug":"lingualchemy-fusing-typological-and","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","date":"2024-01-11","arxiv_id":"2401.06034","repositories_listed":0,"syntology":null},{"url":null,"slug":"hate-speech-and-offensive-content-detection","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","date":"2023-12-09","arxiv_id":"2312.05671","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-text-to-text-model-for-multilingual","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-cross-lingual-sentiment","title":"Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study","date":"2023-11-11","arxiv_id":"2311.06549","repositories_listed":0,"syntology":null},{"url":null,"slug":"medai-dialog-corpus-medic-zero-shot","title":"MedAI Dialog Corpus (MEDIC): Zero-Shot Classification of Doctor and AI Responses in Health Consultations","date":"2023-10-19","arxiv_id":"2310.12489","repositories_listed":0,"syntology":null},{"url":"/paper/mbbc-exploring-the-multilingual-maze","slug":"mbbc-exploring-the-multilingual-maze","title":"Exploring the Maze of Multilingual Modeling","date":"2023-10-09","arxiv_id":"2310.05404","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-distil-bert-code-mixed-language","title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi","date":"2023-09-19","arxiv_id":"2309.10272","repositories_listed":0,"syntology":null},{"url":"/paper/differential-privacy-linguistic-fairness-and","slug":"differential-privacy-linguistic-fairness-and","title":"Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models","date":"2023-08-17","arxiv_id":"2308.08774","repositories_listed":0,"syntology":{"n":23,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/differential-privacy-linguistic-fairness-and#ran","syntology_url":"https://syntology.ai/paper/2308.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08774"}},"official":null}},{"url":null,"slug":"self-distilled-quantization-achieving-high","title":"Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models","date":"2023-07-12","arxiv_id":"2307.05972","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-mbert-understand-romansh-evaluating-word","title":"Does mBERT understand Romansh? Evaluating word embeddings using word alignment","date":"2023-06-14","arxiv_id":"2306.08702","repositories_listed":0,"syntology":null},{"url":null,"slug":"extrapolating-multilingual-understanding","title":"Extrapolating Multilingual Understanding Models as Multilingual Generators","date":"2023-05-22","arxiv_id":"2305.13140","repositories_listed":0,"syntology":null},{"url":null,"slug":"dn-at-semeval-2023-task-12-low-resource","title":"DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning","date":"2023-05-04","arxiv_id":"2305.02607","repositories_listed":0,"syntology":null},{"url":null,"slug":"ustc-nelslip-at-semeval-2023-task-2","title":"USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER","date":"2023-05-04","arxiv_id":"2305.02517","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-to-a-low-resource-language-via-close","title":"Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese","date":"2023-04-18","arxiv_id":"2304.08823","repositories_listed":0,"syntology":null},{"url":null,"slug":"tollywood-emotions-annotation-of-valence","title":"Tollywood Emotions: Annotation of Valence-Arousal in Telugu Song Lyrics","date":"2023-03-16","arxiv_id":"2303.09364","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-semantic-information-into-sketchy","title":"Integrating Semantic Information into Sketchy Reading Module of Retro-Reader for Vietnamese Machine Reading Comprehension","date":"2023-01-01","arxiv_id":"2301.00429","repositories_listed":0,"syntology":null},{"url":null,"slug":"vtcc-nlp-at-nl4opt-competition-subtask-1-an","title":"VTCC-NLP at NL4Opt competition subtask 1: An Ensemble Pre-trained language models for Named Entity Recognition","date":"2022-12-14","arxiv_id":"2212.07219","repositories_listed":0,"syntology":null},{"url":null,"slug":"languages-you-know-influence-those-you-learn","title":"Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer","date":"2022-12-04","arxiv_id":"2212.01757","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-cross-lingual-multi-task-models","title":"Compressing Cross-Lingual Multi-Task Models at Qualtrics","date":"2022-11-29","arxiv_id":"2211.15927","repositories_listed":0,"syntology":null},{"url":null,"slug":"l3cube-hindbert-and-devbert-pre-trained-bert","title":"L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages","date":"2022-11-21","arxiv_id":"2211.11418","repositories_listed":0,"syntology":null},{"url":null,"slug":"legal-tech-open-diaries-lesson-learned-on-how","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","date":"2022-10-24","arxiv_id":"2210.13086","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-word-level-quality-estimation-for","title":"Extending Word-Level Quality Estimation for Post-Editing Assistance","date":"2022-09-23","arxiv_id":"2209.11378","repositories_listed":0,"syntology":null},{"url":null,"slug":"smtce-a-social-media-text-classification","title":"SMTCE: A Social Media Text Classification Evaluation Benchmark and BERTology Models for Vietnamese","date":"2022-09-21","arxiv_id":"2209.10482","repositories_listed":0,"syntology":null},{"url":null,"slug":"alexsis-pt-a-new-resource-for-portuguese","title":"ALEXSIS-PT: A New Resource for Portuguese Lexical Simplification","date":"2022-09-19","arxiv_id":"2209.09034","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-language-relationships-in","title":"Investigating Language Relationships in Multilingual Sentence Encoders Through the Lens of Linguistic Typology","date":"2022-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bertifying-sinhala-a-comprehensive-analysis","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","date":"2022-08-16","arxiv_id":"2208.07864","repositories_listed":0,"syntology":null},{"url":null,"slug":"babelbert-massively-multilingual-transformers","title":"Massively Multilingual Lexical Specialization of Multilingual Transformers","date":"2022-08-01","arxiv_id":"2208.01018","repositories_listed":0,"syntology":null},{"url":null,"slug":"asner-annotated-dataset-and-baseline-for","title":"AsNER -- Annotated Dataset and Baseline for Assamese Named Entity recognition","date":"2022-07-07","arxiv_id":"2207.03422","repositories_listed":0,"syntology":null},{"url":null,"slug":"hitachi-at-semeval-2022-task-2-on-the","title":"Hitachi at SemEval-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sliced-at-semeval-2022-task-11-bigger-better","title":"Sliced at SemEval-2022 Task 11: Bigger, Better? Massively Multilingual LMs for Multilingual Complex NER on an Academic GPU Budget","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"alexa-teacher-model-pretraining-and","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","date":"2022-06-15","arxiv_id":"2206.07808","repositories_listed":0,"syntology":null},{"url":null,"slug":"asner-annotated-dataset-and-baseline-for-1","title":"AsNER - Annotated Dataset and Baseline for Assamese Named Entity recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"debating-europe-a-multilingual-multi-target","title":"Debating Europe: A Multilingual Multi-Target Stance Classification Dataset of Online Debates","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-the-mono-and-cross-lingual","title":"Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models","date":"2022-05-24","arxiv_id":"2205.11758","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-lscdiscovery-shared-task-glossreader-at","title":"black[LSCDiscovery shared task] GlossReader at LSCDiscovery: Train to Select a Proper Gloss in English – Discover Lexical Semantic Change in Spanish","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cuet-nlp-tamilnlp-acl2022-multi-class-textual","title":"CUET-NLP@TamilNLP-ACL2022: Multi-Class Textual Emotion Detection from Social Media using Transformer","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"teluguner-leveraging-multi-domain-named","title":"TeluguNER: Leveraging Multi-Domain Named Entity Recognition with Deep Transformers","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"do-not-fire-the-linguist-grammatical-profiles","title":"Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change","date":"2022-04-12","arxiv_id":"2204.05717","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-multilingual-language-models-capture","title":"Do Multilingual Language Models Capture Differing Moral Norms?","date":"2022-03-18","arxiv_id":"2203.09904","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-ability-of-multilingual-masked","title":"Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure","date":"2022-03-16","arxiv_id":"2203.08430","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-pretrained-multilingual-models-equally","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"frustratingly-simple-regularization-to","title":"Frustratingly Simple Regularization to Improve Zero-shot Cross-lingual Robustness","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lexicon-based-fine-tuning-of-multilingual","title":"Lexicon based Fine-tuning of Multilingual Language Models for Sentiment Analysis of Low-resource Languages","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-cross-lingual-adjustment-of","title":"The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zeroberto-leveraging-zero-shot-text","title":"ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling","date":"2022-01-04","arxiv_id":"2201.01337","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-pre-training-with-universal","title":"Multilingual Pre-training with Universal Dependency Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-static-and-contextualised","title":"Combining static and contextualised multilingual embeddings","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-sparsification-for-emph-masked-fine","title":"Gradient Sparsification For \\emph{Masked Fine-Tuning} of Transformers","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-distillation-framework-for-cross","title":"Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"prix-lm-pretraining-for-multilingual-1","title":"Prix-LM: Pretraining for Multilingual Knowledge Base Construction","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nict-kyoto-submission-for-the-wmt21-quality","title":"NICT Kyoto Submission for the WMT’21 Quality Estimation Task: Multimetric Multilingual Pretraining for Critical Error Detection","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"saliency-based-multi-view-mixed-language","title":"Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"teet-tunisian-dataset-for-toxic-speech","title":"TEET! Tunisian Dataset for Toxic Speech Detection","date":"2021-10-11","arxiv_id":"2110.05287","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-transformers-for-job-expression","title":"Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting","date":"2021-09-17","arxiv_id":"2109.08597","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-universality-of-deep-contextual","title":"On the Universality of Deep Contextual Language Models","date":"2021-09-15","arxiv_id":"2109.07140","repositories_listed":0,"syntology":null},{"url":null,"slug":"fbert-a-neural-transformer-for-identifying","title":"FBERT: A Neural Transformer for Identifying Offensive Content","date":"2021-09-10","arxiv_id":"2109.05074","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-code-mixed-text-using","title":"Classification of Code-Mixed Text Using Capsule Networks","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"siamese-networks-for-inference-in-malayalam","title":"Siamese Networks for Inference in Malayalam Language Texts","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contributions-of-transformer-attention-heads","title":"Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks","date":"2021-08-18","arxiv_id":"2108.08375","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-occams-razor-to-transformer-based","title":"Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arbert-marbert-deep-bidirectional-1","title":"ARBERT \\& MARBERT: Deep Bidirectional Transformers for Arabic","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"glossreader-at-semeval-2021-task-2-reading","title":"GlossReader at SemEval-2021 Task 2: Reading Definitions Improves Contextualized Word Embeddings","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ibm-mnlp-ie-at-case-2021-task-1-multigranular","title":"IBM MNLP IE at CASE 2021 Task 1: Multigranular and Multilingual Event Detection on Protest News","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"li-yong-yu-yi-guan-lian-zeng-qiang-de-kua-yu","title":"利用语义关联增强的跨语言预训练模型的译文质量评估(A Cross-language Pre-trained Model with Enhanced Semantic Connection for MT Quality Estimation)","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"liori-at-semeval-2021-task-2-span-prediction","title":"LIORI at SemEval-2021 Task 2: Span Prediction and Binary Classification approaches to Word-in-Context Disambiguation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robertnlp-at-the-iwpt-2021-shared-task-simple","title":"RobertNLP at the IWPT 2021 Shared Task: Simple Enhanced UD Parsing for 17 Languages","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"skoltechnlp-at-semeval-2021-task-2-generating","title":"SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"team-dadefrni-at-case-2021-task-1-document","title":"Team “DaDeFrNi” at CASE 2021 Task 1: Document and Sentence Classification for Protest Event Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emotion-stimulus-detection-in-german-news","title":"Emotion Stimulus Detection in German News Headlines","date":"2021-07-27","arxiv_id":"2107.12920","repositories_listed":0,"syntology":null},{"url":null,"slug":"tgif-tree-graph-integrated-format-parser-for","title":"TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning","date":"2021-07-14","arxiv_id":"2107.06907","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-primer-on-pretrained-multilingual-language","title":"A Primer on Pretrained Multilingual Language Models","date":"2021-07-01","arxiv_id":"2107.00676","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-sexism-detection-with-multilingual","title":"Automatic Sexism Detection with Multilingual Transformer Models","date":"2021-06-09","arxiv_id":"2106.04908","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-adapt-your-pretrained-multilingual","title":"How to Adapt Your Pretrained Multilingual Model to 1600 Languages","date":"2021-06-03","arxiv_id":"2106.02124","repositories_listed":0,"syntology":null},{"url":null,"slug":"diagnosing-transformers-in-task-oriented","title":"Diagnosing Transformers in Task-Oriented Semantic Parsing","date":"2021-05-27","arxiv_id":"2105.13496","repositories_listed":0,"syntology":null},{"url":null,"slug":"larger-scale-transformers-for-multilingual","title":"Larger-Scale Transformers for Multilingual Masked Language Modeling","date":"2021-05-02","arxiv_id":"2105.00572","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-and-zero-shot-is-closing-in-on","title":"Multilingual and Zero-Shot is Closing in on Monolingual Web Register Classification","date":"2021-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mcl-iitk-at-semeval-2021-task-2-multilingual","title":"MCL@IITK at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation using Augmented Data, Signals, and Transformers","date":"2021-04-04","arxiv_id":"2104.01567","repositories_listed":0,"syntology":null},{"url":null,"slug":"priberam-labs-at-the-3rd-shared-task-on","title":"Priberam Labs at the 3rd Shared Task on SlavNER","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lightmbert-a-simple-yet-effective-method-for","title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","date":"2021-03-11","arxiv_id":"2103.06418","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-difficulty-classification-of-arabic","title":"Automatic Difficulty Classification of Arabic Sentences","date":"2021-03-07","arxiv_id":"2103.04386","repositories_listed":0,"syntology":null},{"url":null,"slug":"vyakarana-a-colorless-green-benchmark-for","title":"Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages","date":"2021-03-01","arxiv_id":"2103.00854","repositories_listed":0,"syntology":null}],"record_sha256":"ea5e871f8a3feecaff4eeb407a10812672dfd5b981f2667de2900f6bd2adcbd0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}