{"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/3","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":3,"pages_in_order":7,"rows_per_page":100,"rows":[201,300],"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/papers/2","next":"/task/document-classification/papers/4","papers":[{"url":"/paper/using-j-k-fold-cross-validation-to-reduce","slug":"using-j-k-fold-cross-validation-to-reduce","title":"Using J-K fold Cross Validation to Reduce Variance When Tuning NLP Models","date":"2018-06-19","arxiv_id":"1806.07139","repositories_listed":1,"syntology":null},{"url":"/paper/multiview-learning-of-weighted-majority-vote","slug":"multiview-learning-of-weighted-majority-vote","title":"Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization","date":"2018-05-25","arxiv_id":"1805.10212","repositories_listed":1,"syntology":null},{"url":"/paper/a-la-carte-embedding-cheap-but-effective","slug":"a-la-carte-embedding-cheap-but-effective","title":"A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors","date":"2018-05-14","arxiv_id":"1805.05388","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-la-carte-embedding-cheap-but-effective#ran","syntology_url":"https://syntology.ai/paper/1805.05388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.05388"}},"official":{"repos":["NLPrinceton/ALaCarte"],"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/rmdl-random-multimodel-deep-learning-for","slug":"rmdl-random-multimodel-deep-learning-for","title":"RMDL: Random Multimodel Deep Learning for Classification","date":"2018-05-03","arxiv_id":"1805.01890","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-multi-class-sentiment","slug":"multilingual-multi-class-sentiment","title":"Multilingual Multi-class Sentiment Classification Using Convolutional Neural Networks","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-machine-learning-algorithms","slug":"a-comparison-of-machine-learning-algorithms","title":"A Comparison of Machine Learning Algorithms for the Surveillance of Autism Spectrum Disorder","date":"2018-04-17","arxiv_id":"1804.06223","repositories_listed":1,"syntology":null},{"url":"/paper/reviving-and-improving-recurrent-back","slug":"reviving-and-improving-recurrent-back","title":"Reviving and Improving Recurrent Back-Propagation","date":"2018-03-16","arxiv_id":"1803.06396","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reviving-and-improving-recurrent-back#ran","syntology_url":"https://syntology.ai/paper/1803.06396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06396"}},"official":{"repos":["lrjconan/RBP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-longer-term-dependencies-in-rnns","slug":"learning-longer-term-dependencies-in-rnns","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","date":"2018-03-01","arxiv_id":"1803.00144","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-detection-on-tv-show-transcripts-with","slug":"emotion-detection-on-tv-show-transcripts-with","title":"Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks","date":"2017-08-14","arxiv_id":"1708.04299","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-vector-representation-for-documents","slug":"efficient-vector-representation-for-documents","title":"Efficient Vector Representation for Documents through Corruption","date":"2017-07-08","arxiv_id":"1707.02377","repositories_listed":1,"syntology":null},{"url":"/paper/using-titles-vs-full-text-as-source-for","slug":"using-titles-vs-full-text-as-source-for","title":"Using Titles vs. Full-text as Source for Automated Semantic Document Annotation","date":"2017-05-15","arxiv_id":"1705.05311","repositories_listed":1,"syntology":null},{"url":"/paper/kate-k-competitive-autoencoder-for-text","slug":"kate-k-competitive-autoencoder-for-text","title":"KATE: K-Competitive Autoencoder for Text","date":"2017-05-04","arxiv_id":"1705.02033","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-semantic-knowledge-into-lexical","slug":"integrating-semantic-knowledge-into-lexical","title":"Integrating Semantic Knowledge into Lexical Embeddings Based on Information Content Measurement","date":"2017-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dirichlet-vmf-mixture-model","slug":"dirichlet-vmf-mixture-model","title":"Dirichlet-vMF Mixture Model","date":"2017-02-24","arxiv_id":"1702.07495","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-word-movers-distance","slug":"supervised-word-movers-distance","title":"Supervised Word Mover's Distance","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-graph-degeneracy-based-approach-to-keyword","slug":"a-graph-degeneracy-based-approach-to-keyword","title":"A Graph Degeneracy-based Approach to Keyword Extraction","date":"2016-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-neural-network-language-models","slug":"convolutional-neural-network-language-models","title":"Convolutional Neural Network Language Models","date":"2016-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-topic-embedding-a-continuous","slug":"generative-topic-embedding-a-continuous","title":"Generative Topic Embedding: a Continuous Representation of Documents","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/meta-a-unified-toolkit-for-text-retrieval-and","slug":"meta-a-unified-toolkit-for-text-retrieval-and","title":"MeTA: A Unified Toolkit for Text Retrieval and Analysis","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-crosslingual-word-embeddings-without","slug":"learning-crosslingual-word-embeddings-without","title":"Learning Crosslingual Word Embeddings without Bilingual Corpora","date":"2016-06-30","arxiv_id":"1606.09403","repositories_listed":1,"syntology":null},{"url":"/paper/active-discriminative-text-representation","slug":"active-discriminative-text-representation","title":"Active Discriminative Text Representation Learning","date":"2016-06-14","arxiv_id":"1606.04212","repositories_listed":1,"syntology":null},{"url":"/paper/generative-topic-embedding-a-continuous-1","slug":"generative-topic-embedding-a-continuous-1","title":"Generative Topic Embedding: a Continuous Representation of Documents (Extended Version with Proofs)","date":"2016-06-09","arxiv_id":"1606.02979","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-job-title-classification-system","slug":"towards-a-job-title-classification-system","title":"Towards a Job Title Classification System","date":"2016-06-02","arxiv_id":"1606.00917","repositories_listed":1,"syntology":null},{"url":"/paper/awhy-should-i-trust-youa-explaining-the","slug":"awhy-should-i-trust-youa-explaining-the","title":"``Why Should I Trust You?'': Explaining the Predictions of Any Classifier","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-attention-networks-for-document","slug":"hierarchical-attention-networks-for-document","title":"Hierarchical Attention Networks for Document Classification","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unimelb-at-semeval-2016-tasks-4a-and-4b-an","slug":"unimelb-at-semeval-2016-tasks-4a-and-4b-an","title":"UNIMELB at SemEval-2016 Tasks 4A and 4B: An Ensemble of Neural Networks and a Word2Vec Based Model for Sentiment Classification","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/openxbow-introducing-the-passau-open-source","slug":"openxbow-introducing-the-passau-open-source","title":"openXBOW - Introducing the Passau Open-Source Crossmodal Bag-of-Words Toolkit","date":"2016-05-22","arxiv_id":"1605.06778","repositories_listed":1,"syntology":null},{"url":"/paper/multivec-a-multilingual-and-multilevel","slug":"multivec-a-multilingual-and-multilevel","title":"MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP","date":"2016-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bridge-correlational-neural-networks-for","slug":"bridge-correlational-neural-networks-for","title":"Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning","date":"2015-10-13","arxiv_id":"1510.03519","repositories_listed":1,"syntology":null},{"url":"/paper/document-classification-by-inversion-of","slug":"document-classification-by-inversion-of","title":"Document Classification by Inversion of Distributed Language Representations","date":"2015-04-27","arxiv_id":"1504.07295","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-monolingual-data-for-crosslingual","slug":"leveraging-monolingual-data-for-crosslingual","title":"Leveraging Monolingual Data for Crosslingual Compositional Word Representations","date":"2014-12-19","arxiv_id":"1412.6334","repositories_listed":1,"syntology":null},{"url":"/paper/anytime-active-learning","slug":"anytime-active-learning","title":"Anytime Active Learning","date":"2014-07-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-models-for-compositional","slug":"multilingual-models-for-compositional","title":"Multilingual Models for Compositional Distributed Semantics","date":"2014-04-17","arxiv_id":"1404.4641","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-distributed-representations","slug":"multilingual-distributed-representations","title":"Multilingual Distributed Representations without Word Alignment","date":"2013-12-20","arxiv_id":"1312.6173","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-topic-coherence-over-many-models","slug":"exploring-topic-coherence-over-many-models","title":"Exploring Topic Coherence over Many Models and Many Topics","date":"2012-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"on-importance-of-layer-pruning-for-smaller","title":"On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages","date":"2025-01-01","arxiv_id":"2501.00733","repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-multi-label-completion-for-semantic","title":"Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning","date":"2024-12-18","arxiv_id":"2412.13809","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-prompting-and-few-shot-fine-tuning","title":"Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models","date":"2024-12-18","arxiv_id":"2412.13859","repositories_listed":0,"syntology":null},{"url":null,"slug":"wordvis-a-color-worth-a-thousand-words","title":"WordVIS: A Color Worth A Thousand Words","date":"2024-12-13","arxiv_id":"2412.10155","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-serve-as-effective","title":"Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale?","date":"2024-12-06","arxiv_id":"2412.05137","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-meets-prototypes-towards","title":"Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks","date":"2024-12-04","arxiv_id":"2412.03761","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-document-ai-data-generation-through","title":"Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts","date":"2024-11-27","arxiv_id":"2412.03590","repositories_listed":0,"syntology":null},{"url":null,"slug":"clustering-algorithms-and-rag-enhancing-semi","title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","date":"2024-11-09","arxiv_id":"2411.06175","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-gat-cancer-document-classification","title":"Medical-GAT: Cancer Document Classification Leveraging Graph-Based Residual Network for Scenarios with Limited Data","date":"2024-10-19","arxiv_id":"2410.15198","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-diagnosis-identification","title":"Weakly-supervised diagnosis identification from Italian discharge letters","date":"2024-10-19","arxiv_id":"2410.15051","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-classification-using-graph-convolutional","title":"Text Classification using Graph Convolutional Networks: A Comprehensive Survey","date":"2024-10-12","arxiv_id":"2410.09399","repositories_listed":0,"syntology":null},{"url":null,"slug":"manual-verbalizer-enrichment-for-few-shot","title":"Manual Verbalizer Enrichment for Few-Shot Text Classification","date":"2024-10-08","arxiv_id":"2410.06173","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-tree-fusion-model-with-bidirectional","title":"Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification","date":"2024-10-03","arxiv_id":"2410.02930","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-type-classification-using-file-names","title":"Document Type Classification using File Names","date":"2024-10-02","arxiv_id":"2410.01166","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14162","title":"On Importance of Pruning and Distillation for Efficient Low Resource NLP","date":"2024-09-21","arxiv_id":"2409.14162","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-encoder-models-for-zero-shot","title":"Prompting Encoder Models for Zero-Shot Classification: A Cross-Domain Study in Italian","date":"2024-07-30","arxiv_id":"2407.20654","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-modal-transformer-for","title":"Hierarchical Multi-modal Transformer for Cross-modal Long Document Classification","date":"2024-07-14","arxiv_id":"2407.10105","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-biomedical-research-classification-the","title":"Rapid Biomedical Research Classification: The Pandemic PACT Advanced Categorisation Engine","date":"2024-07-14","arxiv_id":"2407.10086","repositories_listed":0,"syntology":null},{"url":null,"slug":"focus-on-the-core-efficient-attention-via","title":"Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification","date":"2024-06-03","arxiv_id":"2406.01283","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxiliary-knowledge-induced-learning-for","title":"Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification","date":"2024-05-29","arxiv_id":"2405.19084","repositories_listed":0,"syntology":null},{"url":"/paper/evaluation-of-large-language-model","slug":"evaluation-of-large-language-model","title":"Evaluation of large language model performance on the Biomedical Language Understanding and Reasoning Benchmark","date":"2024-05-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-long-text-understanding-with","title":"Improving Long Text Understanding with Knowledge Distilled from Summarization Model","date":"2024-05-08","arxiv_id":"2405.04955","repositories_listed":0,"syntology":null},{"url":null,"slug":"cica-content-injected-contrastive-alignment","title":"CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification","date":"2024-05-06","arxiv_id":"2405.03660","repositories_listed":0,"syntology":null},{"url":null,"slug":"guidewalk-heterogeneous-data-fusion-for","title":"GuideWalk: A Novel Graph-Based Word Embedding for Enhanced Text Classification","date":"2024-04-25","arxiv_id":"2404.18942","repositories_listed":0,"syntology":null},{"url":null,"slug":"buddie-a-business-document-dataset-for-multi","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","date":"2024-04-05","arxiv_id":"2404.04003","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-healthcare-language-model","title":"Developing Healthcare Language Model Embedding Spaces","date":"2024-03-28","arxiv_id":"2403.19802","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlp-for-knowledge-discovery-and-information","title":"NLP for Knowledge Discovery and Information Extraction from Energetics Corpora","date":"2024-02-10","arxiv_id":"2402.06964","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-models-for-the-detection-of-hate","title":"Efficient Models for the Detection of Hate, Abuse and Profanity","date":"2024-02-08","arxiv_id":"2402.05624","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-learning-oriented-dlp-system-based-on","title":"A Learning oriented DLP System based on Classification Model","date":"2023-12-21","arxiv_id":"2312.13711","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversifying-knowledge-enhancement-of","title":"Diversifying Knowledge Enhancement of Biomedical Language Models using Adapter Modules and Knowledge Graphs","date":"2023-12-21","arxiv_id":"2312.13881","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-in-healthcare-and","title":"Large language models in healthcare and medical domain: A review","date":"2023-12-12","arxiv_id":"2401.06775","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-section-weights-for-multi-label","title":"Learning Section Weights for Multi-Label Document Classification","date":"2023-11-26","arxiv_id":"2311.15402","repositories_listed":0,"syntology":null},{"url":null,"slug":"atlantic-structure-aware-retrieval-augmented","title":"ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science","date":"2023-11-21","arxiv_id":"2311.12289","repositories_listed":0,"syntology":null},{"url":null,"slug":"causality-is-all-you-need","title":"Causality is all you need","date":"2023-11-21","arxiv_id":"2311.12307","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-text-classification-techniques-in","title":"Explainable Text Classification Techniques in Legal Document Review: Locating Rationales without Using Human Annotated Training Text Snippets","date":"2023-11-15","arxiv_id":"2311.09133","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-modal-multilingual-benchmark-for","title":"A Multi-Modal Multilingual Benchmark for Document Image Classification","date":"2023-10-25","arxiv_id":"2310.16356","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-document-information-analysis-with","title":"Enhancing Document Information Analysis with Multi-Task Pre-training: A Robust Approach for Information Extraction in Visually-Rich Documents","date":"2023-10-25","arxiv_id":"2310.16527","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-on-large-language-models-in","title":"An Analysis on Large Language Models in Healthcare: A Case Study of BioBERT","date":"2023-10-11","arxiv_id":"2310.07282","repositories_listed":0,"syntology":null},{"url":null,"slug":"kobigbird-large-transformation-of-transformer","title":"KoBigBird-large: Transformation of Transformer for Korean Language Understanding","date":"2023-09-19","arxiv_id":"2309.10339","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-extraction-using-deep-generative","title":"Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Dataset","date":"2023-08-21","arxiv_id":"2308.13545","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-materials-language-processing","title":"Accelerated materials language processing enabled by GPT","date":"2023-08-18","arxiv_id":"2308.09354","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-prompt-chaining-for-long","title":"Large Language Model Prompt Chaining for Long Legal Document Classification","date":"2023-08-08","arxiv_id":"2308.04138","repositories_listed":0,"syntology":null},{"url":null,"slug":"laficmil-rethinking-large-file-classification","title":"LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning","date":"2023-07-30","arxiv_id":"2308.01413","repositories_listed":0,"syntology":null},{"url":null,"slug":"incrementally-computable-neural-networks","title":"Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs","date":"2023-07-27","arxiv_id":"2307.14988","repositories_listed":0,"syntology":null},{"url":null,"slug":"umls-kgi-bert-data-centric-knowledge","title":"UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition","date":"2023-07-20","arxiv_id":"2307.11170","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-over-pre-trained-sentence","title":"Attention over pre-trained Sentence Embeddings for Long Document Classification","date":"2023-07-18","arxiv_id":"2307.09084","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-sentiment-analysis-of-plastic","title":"Unsupervised Sentiment Analysis of Plastic Surgery Social Media Posts","date":"2023-07-05","arxiv_id":"2307.02640","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-evaluation-of-document-classification","title":"On Evaluation of Document Classification using RVL-CDIP","date":"2023-06-21","arxiv_id":"2306.12550","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-chatgpt-on-biomedical-tasks-a","title":"Evaluation of ChatGPT on Biomedical Tasks: A Zero-Shot Comparison with Fine-Tuned Generative Transformers","date":"2023-06-07","arxiv_id":"2306.04504","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-unet-with-multi-headed","title":"Transformer-Based UNet with Multi-Headed Cross-Attention Skip Connections to Eliminate Artifacts in Scanned Documents","date":"2023-06-05","arxiv_id":"2306.02815","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-document-classification-and-key","title":"End-to-End Document Classification and Key Information Extraction using Assignment Optimization","date":"2023-06-01","arxiv_id":"2306.00750","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-natural-language-processing-for-long","title":"Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization","date":"2023-05-25","arxiv_id":"2305.16259","repositories_listed":0,"syntology":null},{"url":"/paper/dublin-document-understanding-by-language","slug":"dublin-document-understanding-by-language","title":"DUBLIN -- Document Understanding By Language-Image Network","date":"2023-05-23","arxiv_id":"2305.14218","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlue-benchmarking-document-language","title":"DLUE: Benchmarking Document Language Understanding","date":"2023-05-16","arxiv_id":"2305.09520","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-bert-language-model-for-arabic","title":"Leveraging BERT Language Model for Arabic Long Document Classification","date":"2023-05-04","arxiv_id":"2305.03519","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-information-theory-of-certainty-for","title":"A New Information Theory of Certainty for Machine Learning","date":"2023-04-25","arxiv_id":"2304.12833","repositories_listed":0,"syntology":null},{"url":null,"slug":"hero-roberta-and-longformer-hebrew-language","title":"HeRo: RoBERTa and Longformer Hebrew Language Models","date":"2023-04-18","arxiv_id":"2304.11077","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-structure-and-style-political","title":"Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy","date":"2023-04-05","arxiv_id":"2304.02247","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-automatic-method-for-document","title":"A semi-automatic method for document classification in the shipping industry","date":"2023-03-29","arxiv_id":"2305.06148","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-the-needle-in-a-haystack-unsupervised","title":"Finding the Needle in a Haystack: Unsupervised Rationale Extraction from Long Text Classifiers","date":"2023-03-14","arxiv_id":"2303.07991","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-nonnegative-matrix-factorization-for","title":"Neural Nonnegative Matrix Factorization for Hierarchical Multilayer Topic Modeling","date":"2023-02-28","arxiv_id":"2303.00058","repositories_listed":0,"syntology":null},{"url":null,"slug":"elementwise-language-representation","title":"Elementwise Language Representation","date":"2023-02-27","arxiv_id":"2302.13475","repositories_listed":0,"syntology":null},{"url":null,"slug":"fewshottextgcn-k-hop-neighborhood","title":"FewShotTextGCN: K-hop neighborhood regularization for few-shot learning on graphs","date":"2023-01-25","arxiv_id":"2301.10481","repositories_listed":0,"syntology":null},{"url":null,"slug":"hawk-an-industrial-strength-multi-label","title":"Hawk: An Industrial-strength Multi-label Document Classifier","date":"2023-01-15","arxiv_id":"2301.06057","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-in-the-loop-how-to-effectively-create","title":"Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class","date":"2022-12-19","arxiv_id":"2212.09422","repositories_listed":0,"syntology":null}],"record_sha256":"84518377954195e0c636031f0bacac0a183716b446142af29c7d65b1db02c09f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}