{"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/document-classification/papers/2","list_of":"/task/document-classification","task":"Document Classification","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":7,"rows_per_page":100,"rows":[101,200],"of":641,"counts":{"archive_papers_tagged":641,"with_a_code_link":235,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":641,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/document-classification","prev":"/task/document-classification","next":"/task/document-classification/papers/3","papers":[{"url":"/paper/tsetlin-machine-embedding-representing-words","slug":"tsetlin-machine-embedding-representing-words","title":"Tsetlin Machine Embedding: Representing Words Using Logical Expressions","date":"2023-01-02","arxiv_id":"2301.00709","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-out-of-distribution-performance-on","slug":"evaluating-out-of-distribution-performance-on","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","date":"2022-10-14","arxiv_id":"2210.07448","repositories_listed":1,"syntology":null},{"url":"/paper/lbl2vec-an-embedding-based-approach-for","slug":"lbl2vec-an-embedding-based-approach-for","title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","date":"2022-10-12","arxiv_id":"2210.06023","repositories_listed":1,"syntology":null},{"url":"/paper/bl-research-at-semeval-2022-task-8-using","slug":"bl-research-at-semeval-2022-task-8-using","title":"BL.Research at SemEval-2022 Task 8: Using various Semantic Information to evaluate document-level Semantic Textual Similarity","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/supervised-dictionary-learning-with-auxiliary","slug":"supervised-dictionary-learning-with-auxiliary","title":"Supervised Dictionary Learning with Auxiliary Covariates","date":"2022-06-14","arxiv_id":"2206.06774","repositories_listed":1,"syntology":null},{"url":"/paper/chordmixer-a-scalable-neural-attention-model","slug":"chordmixer-a-scalable-neural-attention-model","title":"ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths","date":"2022-06-12","arxiv_id":"2206.05852","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chordmixer-a-scalable-neural-attention-model#ran","syntology_url":"https://syntology.ai/paper/2206.05852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05852"}},"official":{"repos":["ruslankhalitov/chordmixer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ldrnet-enabling-real-time-document","slug":"ldrnet-enabling-real-time-document","title":"LDRNet: Enabling Real-time Document Localization on Mobile Devices","date":"2022-06-05","arxiv_id":"2206.02136","repositories_listed":1,"syntology":null},{"url":"/paper/babybear-cheap-inference-triage-for-expensive","slug":"babybear-cheap-inference-triage-for-expensive","title":"BabyBear: Cheap inference triage for expensive language models","date":"2022-05-24","arxiv_id":"2205.11747","repositories_listed":1,"syntology":null},{"url":"/paper/word-tour-one-dimensional-word-embeddings-via","slug":"word-tour-one-dimensional-word-embeddings-via","title":"Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem","date":"2022-05-04","arxiv_id":"2205.01954","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/word-tour-one-dimensional-word-embeddings-via#ran","syntology_url":"https://syntology.ai/paper/2205.01954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01954"}},"official":{"repos":["joisino/wordtour"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-transformer-based-models-for-long-1","slug":"revisiting-transformer-based-models-for-long-1","title":"Revisiting Transformer-based Models for Long Document Classification","date":"2022-04-14","arxiv_id":"2204.06683","repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-dataset-for-legal-word","slug":"an-evaluation-dataset-for-legal-word","title":"An Evaluation Dataset for Legal Word Embedding: A Case Study On Chinese Codex","date":"2022-03-29","arxiv_id":"2203.15173","repositories_listed":1,"syntology":null},{"url":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}},"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/specialized-document-embeddings-for-aspect","slug":"specialized-document-embeddings-for-aspect","title":"Specialized Document Embeddings for Aspect-based Similarity of Research Papers","date":"2022-03-28","arxiv_id":"2203.14541","repositories_listed":1,"syntology":null},{"url":"/paper/docxclassifier-high-performance-explainable","slug":"docxclassifier-high-performance-explainable","title":"DocXClassifier: High Performance Explainable Deep Network for Document Image Classification","date":"2022-03-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improved-multi-label-classification-under-1","slug":"improved-multi-label-classification-under-1","title":"Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting","date":"2022-03-15","arxiv_id":"2203.07856","repositories_listed":1,"syntology":null},{"url":"/paper/sobolev-transport-a-scalable-metric-for","slug":"sobolev-transport-a-scalable-metric-for","title":"Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics","date":"2022-02-22","arxiv_id":"2202.10723","repositories_listed":1,"syntology":null},{"url":"/paper/one-configuration-to-rule-them-all-towards","slug":"one-configuration-to-rule-them-all-towards","title":"One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization","date":"2022-02-15","arxiv_id":"2202.07631","repositories_listed":1,"syntology":null},{"url":"/paper/neighborhood-contrastive-learning-for-1","slug":"neighborhood-contrastive-learning-for-1","title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","date":"2022-02-14","arxiv_id":"2202.06671","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/neighborhood-contrastive-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2202.06671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06671"}},"official":{"repos":["malteos/scincl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/clinical-longformer-and-clinical-bigbird","slug":"clinical-longformer-and-clinical-bigbird","title":"Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences","date":"2022-01-27","arxiv_id":"2201.11838","repositories_listed":1,"syntology":null},{"url":"/paper/automation-of-citation-screening-for","slug":"automation-of-citation-screening-for","title":"Automation of Citation Screening for Systematic Literature Reviews using Neural Networks: A Replicability Study","date":"2022-01-19","arxiv_id":"2201.07534","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automation-of-citation-screening-for#ran","syntology_url":"https://syntology.ai/paper/2201.07534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.07534"}},"official":{"repos":["projectdossier/citationscreeningreplicability"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ernie-layout-layout-knowledge-enhanced-multi","slug":"ernie-layout-layout-knowledge-enhanced-multi","title":"ERNIE-Layout: Layout-Knowledge Enhanced Multi-modal Pre-training for Document Understanding","date":"2022-01-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sublinear-time-approximation-of-text","slug":"sublinear-time-approximation-of-text","title":"Sublinear Time Approximation of Text Similarity Matrices","date":"2021-12-17","arxiv_id":"2112.09631","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sublinear-time-approximation-of-text#ran","syntology_url":"https://syntology.ai/paper/2112.09631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09631"}},"official":{"repos":["archanray/approximate_similarities"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-structure-learning-via-graph-neural","slug":"sparse-structure-learning-via-graph-neural","title":"Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification","date":"2021-12-13","arxiv_id":"2112.06386","repositories_listed":1,"syntology":null},{"url":"/paper/multieurlex-a-multi-lingual-and-multi-label-1","slug":"multieurlex-a-multi-lingual-and-multi-label-1","title":"MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-concept-map-generation","slug":"weakly-supervised-concept-map-generation","title":"Weakly Supervised Concept Map Generation through Task-Guided Graph Translation","date":"2021-10-08","arxiv_id":"2110.15720","repositories_listed":1,"syntology":null},{"url":"/paper/multieurlex-a-multi-lingual-and-multi-label","slug":"multieurlex-a-multi-lingual-and-multi-label","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","date":"2021-09-02","arxiv_id":"2109.00904","repositories_listed":1,"syntology":null},{"url":"/paper/towards-explaining-stem-document","slug":"towards-explaining-stem-document","title":"Towards Explaining STEM Document Classification using Mathematical Entity Linking","date":"2021-09-02","arxiv_id":"2109.00954","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-for-biomedical-natural-language","slug":"benchmarking-for-biomedical-natural-language","title":"Benchmarking for Biomedical Natural Language Processing Tasks with a Domain Specific ALBERT","date":"2021-07-09","arxiv_id":"2107.04374","repositories_listed":1,"syntology":null},{"url":"/paper/tagruler-interactive-tool-for-span-level-data","slug":"tagruler-interactive-tool-for-span-level-data","title":"TagRuler: Interactive Tool for Span-Level Data Programming by Demonstration","date":"2021-06-24","arxiv_id":"2106.12767","repositories_listed":1,"syntology":null},{"url":"/paper/a-sentence-level-hierarchical-bert-model-for","slug":"a-sentence-level-hierarchical-bert-model-for","title":"A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data","date":"2021-06-12","arxiv_id":"2106.06738","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-cross-lingual-sentence","slug":"lightweight-cross-lingual-sentence","title":"Lightweight Cross-Lingual Sentence Representation Learning","date":"2021-05-28","arxiv_id":"2105.13856","repositories_listed":1,"syntology":null},{"url":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scifive-a-text-to-text-transformer-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.03598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03598"}},"official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-transformer-networks-for","slug":"hierarchical-transformer-networks-for","title":"Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-04-17","arxiv_id":"2104.08444","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-relationship-between-algorithm","slug":"exploring-the-relationship-between-algorithm","title":"Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification","date":"2021-04-08","arxiv_id":"2104.03848","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-document-embedding-via","slug":"unsupervised-document-embedding-via","title":"Unsupervised Document Embedding via Contrastive Augmentation","date":"2021-03-26","arxiv_id":"2103.14542","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-and-cross-lingual-document","slug":"multilingual-and-cross-lingual-document","title":"Multilingual and cross-lingual document classification: A meta-learning approach","date":"2021-01-27","arxiv_id":"2101.11302","repositories_listed":1,"syntology":null},{"url":"/paper/combining-deep-generative-models-and-multi","slug":"combining-deep-generative-models-and-multi","title":"Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification","date":"2021-01-26","arxiv_id":"2101.10717","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-word-embeddings-using-multi-semantic","slug":"enhanced-word-embeddings-using-multi-semantic","title":"Enhanced word embeddings using multi-semantic representation through lexical chains","date":"2021-01-22","arxiv_id":"2101.09023","repositories_listed":1,"syntology":null},{"url":"/paper/banglabert-combating-embedding-barrier-for","slug":"banglabert-combating-embedding-barrier-for","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","date":"2021-01-01","arxiv_id":"2101.00204","repositories_listed":1,"syntology":null},{"url":"/paper/mixing-adam-and-sgd-a-combined-optimization","slug":"mixing-adam-and-sgd-a-combined-optimization","title":"Mixing ADAM and SGD: a Combined Optimization Method","date":"2020-11-16","arxiv_id":"2011.08042","repositories_listed":1,"syntology":null},{"url":"/paper/improving-conversational-question-answering","slug":"improving-conversational-question-answering","title":"Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning","date":"2020-11-01","arxiv_id":"2011.00615","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-metadata-aware-document","slug":"hierarchical-metadata-aware-document","title":"Hierarchical Metadata-Aware Document Categorization under Weak Supervision","date":"2020-10-26","arxiv_id":"2010.13556","repositories_listed":1,"syntology":null},{"url":"/paper/german-s-next-language-model","slug":"german-s-next-language-model","title":"German's Next Language Model","date":"2020-10-21","arxiv_id":"2010.10906","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-few-zero-shot-learning-with","slug":"multi-label-few-zero-shot-learning-with","title":"Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs","date":"2020-10-15","arxiv_id":"2010.07459","repositories_listed":1,"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/multi-label-few-zero-shot-learning-with#ran","syntology_url":"https://syntology.ai/paper/2010.07459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07459"}},"official":{"repos":["MemoriesJ/KAMG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/topicbert-for-energy-efficient-document","slug":"topicbert-for-energy-efficient-document","title":"TopicBERT for Energy Efficient Document Classification","date":"2020-10-15","arxiv_id":"2010.16407","repositories_listed":1,"syntology":null},{"url":"/paper/aspect-based-document-similarity-for-research","slug":"aspect-based-document-similarity-for-research","title":"Aspect-based Document Similarity for Research Papers","date":"2020-10-13","arxiv_id":"2010.06395","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/aspect-based-document-similarity-for-research#ran","syntology_url":"https://syntology.ai/paper/2010.06395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06395"}},"official":{"repos":["malteos/aspect-document-similarity"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-rst-based-evaluation-of-discourse","slug":"neural-rst-based-evaluation-of-discourse","title":"Neural RST-based Evaluation of Discourse Coherence","date":"2020-09-30","arxiv_id":"2009.14463","repositories_listed":1,"syntology":null},{"url":"/paper/data-programming-by-demonstration-a-framework","slug":"data-programming-by-demonstration-a-framework","title":"Data Programming by Demonstration: A Framework for Interactively Learning Labeling Functions","date":"2020-09-03","arxiv_id":"2009.01444","repositories_listed":1,"syntology":null},{"url":"/paper/label-wise-document-pre-training-for-multi","slug":"label-wise-document-pre-training-for-multi","title":"Label-Wise Document Pre-Training for Multi-Label Text Classification","date":"2020-08-15","arxiv_id":"2008.06695","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-fasttext-word-embedding-effects-in","slug":"a-study-of-fasttext-word-embedding-effects-in","title":"A Study of fastText Word Embedding Effects in Document Classification in Bangla Language","date":"2020-07-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-confidence-calibrated-moba-game-winner","slug":"a-confidence-calibrated-moba-game-winner","title":"A Confidence-Calibrated MOBA Game Winner Predictor","date":"2020-06-28","arxiv_id":"2006.15521","repositories_listed":1,"syntology":null},{"url":"/paper/aradic-arabic-document-classification-using-1","slug":"aradic-arabic-document-classification-using-1","title":"AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss","date":"2020-06-20","arxiv_id":"2006.11586","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/aradic-arabic-document-classification-using-1#ran","syntology_url":"https://syntology.ai/paper/2006.11586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11586"}},"official":{"repos":["mahmouddaif/AraDIC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explainable-and-discourse-topic-aware-neural","slug":"explainable-and-discourse-topic-aware-neural","title":"Explainable and Discourse Topic-aware Neural Language Understanding","date":"2020-06-18","arxiv_id":"2006.10632","repositories_listed":1,"syntology":null},{"url":"/paper/lsd-c-linearly-separable-deep-clusters","slug":"lsd-c-linearly-separable-deep-clusters","title":"LSD-C: Linearly Separable Deep Clusters","date":"2020-06-17","arxiv_id":"2006.10039","repositories_listed":1,"syntology":null},{"url":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","repositories_listed":1,"syntology":null},{"url":"/paper/document-classification-for-covid-19","slug":"document-classification-for-covid-19","title":"Document Classification for COVID-19 Literature","date":"2020-06-15","arxiv_id":"2006.13816","repositories_listed":1,"syntology":null},{"url":"/paper/a-pre-training-technique-to-localize-medical","slug":"a-pre-training-technique-to-localize-medical","title":"Pre-training technique to localize medical BERT and enhance biomedical BERT","date":"2020-05-14","arxiv_id":"2005.07202","repositories_listed":1,"syntology":null},{"url":"/paper/performance-evaluation-of-machine-learning-3","slug":"performance-evaluation-of-machine-learning-3","title":"Performance evaluation of Machine learning algorithms in Biomedical Document Classification","date":"2020-05-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/massively-multilingual-sparse-word","slug":"massively-multilingual-sparse-word","title":"Massively Multilingual Sparse Word Representations","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/minimally-supervised-categorization-of-text","slug":"minimally-supervised-categorization-of-text","title":"Minimally Supervised Categorization of Text with Metadata","date":"2020-05-01","arxiv_id":"2005.00624","repositories_listed":1,"syntology":null},{"url":"/paper/a-concept-based-abstraction-aggregation-deep","slug":"a-concept-based-abstraction-aggregation-deep","title":"Corpus-level and Concept-based Explanations for Interpretable Document Classification","date":"2020-04-24","arxiv_id":"2004.13003","repositories_listed":1,"syntology":null},{"url":"/paper/light-weighted-cnn-for-text-classification","slug":"light-weighted-cnn-for-text-classification","title":"Light-Weighted CNN for Text Classification","date":"2020-04-16","arxiv_id":"2004.07922","repositories_listed":1,"syntology":null},{"url":"/paper/keyword-assisted-topic-models","slug":"keyword-assisted-topic-models","title":"Keyword Assisted Topic Models","date":"2020-04-13","arxiv_id":"2004.05964","repositories_listed":1,"syntology":null},{"url":"/paper/classification-benchmarks-for-under-resourced","slug":"classification-benchmarks-for-under-resourced","title":"Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network","date":"2020-04-11","arxiv_id":"2004.07807","repositories_listed":1,"syntology":null},{"url":"/paper/text-classification-with-word-embedding","slug":"text-classification-with-word-embedding","title":"Text classification with word embedding regularization and soft similarity measure","date":"2020-03-10","arxiv_id":"2003.05019","repositories_listed":1,"syntology":null},{"url":"/paper/sets-clustering","slug":"sets-clustering","title":"Sets Clustering","date":"2020-03-09","arxiv_id":"2003.04135","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-models-vs-transfer-learning-for","slug":"hierarchical-models-vs-transfer-learning-for","title":"A Systematic Comparison of Architectures for Document-Level Sentiment Classification","date":"2020-02-19","arxiv_id":"2002.08131","repositories_listed":1,"syntology":null},{"url":"/paper/constrained-relational-topic-models","slug":"constrained-relational-topic-models","title":"Constrained Relational Topic Models","date":"2020-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantic-sensitive-tf-idf-to-determine-word","slug":"semantic-sensitive-tf-idf-to-determine-word","title":"Semantic Sensitive TF-IDF to Determine Word Relevance in Documents","date":"2020-01-06","arxiv_id":"2001.09896","repositories_listed":1,"syntology":null},{"url":"/paper/pyss3-a-python-package-implementing-a-novel","slug":"pyss3-a-python-package-implementing-a-novel","title":"PySS3: A Python package implementing a novel text classifier with visualization tools for Explainable AI","date":"2019-12-19","arxiv_id":"1912.09322","repositories_listed":1,"syntology":null},{"url":"/paper/speeding-up-word-movers-distance-and-its","slug":"speeding-up-word-movers-distance-and-its","title":"Speeding up Word Mover's Distance and its variants via properties of distances between embeddings","date":"2019-12-01","arxiv_id":"1912.00509","repositories_listed":1,"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":0,"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/speeding-up-word-movers-distance-and-its#ran","syntology_url":"https://syntology.ai/paper/1912.00509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00509"}},"official":{"repos":["matwerner/fast-wmd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/my-approach-your-apparatus-entropy-based","slug":"my-approach-your-apparatus-entropy-based","title":"My Approach = Your Apparatus? Entropy-Based Topic Modeling on Multiple Domain-Specific Text Collections","date":"2019-11-25","arxiv_id":"1911.11240","repositories_listed":1,"syntology":null},{"url":"/paper/improving-document-classification-with-multi","slug":"improving-document-classification-with-multi","title":"Improving Document Classification with Multi-Sense Embeddings","date":"2019-11-18","arxiv_id":"1911.07918","repositories_listed":1,"syntology":null},{"url":"/paper/lexipers-an-ontology-based-sentiment-lexicon","slug":"lexipers-an-ontology-based-sentiment-lexicon","title":"LexiPers: An ontology based sentiment lexicon for Persian","date":"2019-11-13","arxiv_id":"1911.05263","repositories_listed":1,"syntology":null},{"url":"/paper/t-ss3-a-text-classifier-with-dynamic-n-grams","slug":"t-ss3-a-text-classifier-with-dynamic-n-grams","title":"t-SS3: a text classifier with dynamic n-grams for early risk detection over text streams","date":"2019-11-11","arxiv_id":"1911.06147","repositories_listed":1,"syntology":null},{"url":"/paper/dfnets-spectral-cnns-for-graphs-with-feedback","slug":"dfnets-spectral-cnns-for-graphs-with-feedback","title":"DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters","date":"2019-10-24","arxiv_id":"1910.10866","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/dfnets-spectral-cnns-for-graphs-with-feedback#ran","syntology_url":"https://syntology.ai/paper/1910.10866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10866"}},"official":{"repos":["wokas36/DFNets"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/enriching-bert-with-knowledge-graph","slug":"enriching-bert-with-knowledge-graph","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","date":"2019-09-18","arxiv_id":"1909.08402","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-domain-gap-in-cross-lingual","slug":"bridging-the-domain-gap-in-cross-lingual","title":"Bridging the domain gap in cross-lingual document classification","date":"2019-09-16","arxiv_id":"1909.07009","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-the-domain-gap-in-cross-lingual#ran","syntology_url":"https://syntology.ai/paper/1909.07009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07009"}},"official":{"repos":["laiguokun/xlu-data"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-robust-hybrid-approach-for-textual-document","slug":"a-robust-hybrid-approach-for-textual-document","title":"A Robust Hybrid Approach for Textual Document Classification","date":"2019-09-12","arxiv_id":"1909.05478","repositories_listed":1,"syntology":null},{"url":"/paper/cate-category-name-guidedword-embedding","slug":"cate-category-name-guidedword-embedding","title":"Discriminative Topic Mining via Category-Name Guided Text Embedding","date":"2019-08-20","arxiv_id":"1908.07162","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-figure-captions-and-descriptive","slug":"incorporating-figure-captions-and-descriptive","title":"Incorporating Figure Captions and Descriptive Text in MeSH Term Indexing","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-uncertainty-in-document-1","slug":"mitigating-uncertainty-in-document-1","title":"Mitigating Uncertainty in Document Classification","date":"2019-07-17","arxiv_id":"1907.07590","repositories_listed":1,"syntology":null},{"url":"/paper/neural-temporality-adaptation-for-document","slug":"neural-temporality-adaptation-for-document","title":"Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-of-discourse-aware-text","slug":"unsupervised-learning-of-discourse-aware-text","title":"Unsupervised Learning of Discourse-Aware Text Representation for Essay Scoring","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-user-factor-adaptation-for-text","slug":"neural-user-factor-adaptation-for-text","title":"Neural User Factor Adaptation for Text Classification: Learning to Generalize Across Author Demographics","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-complex-neural-network","slug":"rethinking-complex-neural-network","title":"Rethinking Complex Neural Network Architectures for Document Classification","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/190600095","slug":"190600095","title":"The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning","date":"2019-05-31","arxiv_id":"1906.00095","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-deep-learning-networks-for","slug":"object-detection-deep-learning-networks-for","title":"Object detection deep learning networks for Optical Character Recognition","date":"2019-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adaptively-connected-neural-networks","slug":"adaptively-connected-neural-networks","title":"Adaptively Connected Neural Networks","date":"2019-04-07","arxiv_id":"1904.03579","repositories_listed":1,"syntology":null},{"url":"/paper/hpi-dhc-at-trec-2018-precision-medicine-track","slug":"hpi-dhc-at-trec-2018-precision-medicine-track","title":"HPI-DHC at TREC 2018 Precision Medicine Track","date":"2018-11-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-text-classification-via-image","slug":"end-to-end-text-classification-via-image","title":"End-to-End Text Classification via Image-based Embedding using Character-level Networks","date":"2018-10-08","arxiv_id":"1810.03595","repositories_listed":1,"syntology":null},{"url":"/paper/speed-reading-learning-to-read-forbackward","slug":"speed-reading-learning-to-read-forbackward","title":"Speed Reading: Learning to Read ForBackward via Shuttle","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/paraphrase-thought-sentence-embedding-module","slug":"paraphrase-thought-sentence-embedding-module","title":"Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition","date":"2018-08-16","arxiv_id":"1808.05505","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-learnable-graph-convolutional","slug":"large-scale-learnable-graph-convolutional","title":"Large-Scale Learnable Graph Convolutional Networks","date":"2018-08-12","arxiv_id":"1808.03965","repositories_listed":1,"syntology":null},{"url":"/paper/authorless-topic-models-biasing-models-away","slug":"authorless-topic-models-biasing-models-away","title":"Authorless Topic Models: Biasing Models Away from Known Structure","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/using-j-k-fold-cross-validation-to-reduce-1","slug":"using-j-k-fold-cross-validation-to-reduce-1","title":"Using J-K-fold Cross Validation To Reduce Variance When Tuning NLP Models","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/examining-temporality-in-document","slug":"examining-temporality-in-document","title":"Examining Temporality in Document Classification","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/inter-and-intra-topic-structure-learning-with","slug":"inter-and-intra-topic-structure-learning-with","title":"Inter and Intra Topic Structure Learning with Word Embeddings","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/subword-level-word-vector-representations-for","slug":"subword-level-word-vector-representations-for","title":"Subword-level Word Vector Representations for Korean","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"523286ccdab1c2b3116355f07cee96558f0a706e951f077c76f581e6dc250197","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}