{"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-understanding/papers/3","list_of":"/task/document-understanding","task":"document understanding","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":4,"rows_per_page":100,"rows":[201,300],"of":309,"counts":{"archive_papers_tagged":309,"with_a_code_link":140,"where_syntology_ran_a_sample":39,"not_listed_spam_title":0,"listed":309,"listed_where_code_ran":39,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":9,"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-understanding","prev":"/task/document-understanding/papers/2","next":"/task/document-understanding/papers/4","papers":[{"url":null,"slug":"distildoc-knowledge-distillation-for-visually","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","date":"2024-06-12","arxiv_id":"2406.08226","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-structured-generation","title":"Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use","date":"2024-05-30","arxiv_id":"2405.20245","repositories_listed":0,"syntology":null},{"url":null,"slug":"notes-on-applicability-of-gpt-4-to-document","title":"Notes on Applicability of GPT-4 to Document Understanding","date":"2024-05-28","arxiv_id":"2405.18433","repositories_listed":0,"syntology":null},{"url":null,"slug":"crepe-coordinate-aware-end-to-end-document","title":"CREPE: Coordinate-Aware End-to-End Document Parser","date":"2024-05-01","arxiv_id":"2405.00260","repositories_listed":0,"syntology":null},{"url":"/paper/a-layoutlmv3-based-model-for-enhanced","slug":"a-layoutlmv3-based-model-for-enhanced","title":"A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents","date":"2024-04-16","arxiv_id":"2404.10848","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-resume-understanding-a","title":"Towards Efficient Resume Understanding: A Multi-Granularity Multi-Modal Pre-Training Approach","date":"2024-04-13","arxiv_id":"2404.13067","repositories_listed":0,"syntology":null},{"url":null,"slug":"hrvda-high-resolution-visual-document","title":"HRVDA: High-Resolution Visual Document Assistant","date":"2024-04-10","arxiv_id":"2404.06918","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":"can-ai-models-appreciate-document-aesthetics","title":"Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence","date":"2024-03-27","arxiv_id":"2403.18183","repositories_listed":0,"syntology":null},{"url":null,"slug":"layoutllm-large-language-model-instruction","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","date":"2024-03-21","arxiv_id":"2403.14252","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-visual-document-understanding-with","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","date":"2024-02-29","arxiv_id":"2402.19014","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfret-dvqa-coarse-to-fine-retrieval-and","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","date":"2024-02-26","arxiv_id":"2403.00816","repositories_listed":0,"syntology":null},{"url":null,"slug":"rjua-meddqa-a-multimodal-benchmark-for","title":"RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning","date":"2024-02-19","arxiv_id":"2402.14840","repositories_listed":0,"syntology":null},{"url":"/paper/lapdoc-layout-aware-prompting-for-documents","slug":"lapdoc-layout-aware-prompting-for-documents","title":"LAPDoc: Layout-Aware Prompting for Documents","date":"2024-02-15","arxiv_id":"2402.09841","repositories_listed":0,"syntology":null},{"url":null,"slug":"longfin-a-multimodal-document-understanding","title":"LongFin: A Multimodal Document Understanding Model for Long Financial Domain Documents","date":"2024-01-26","arxiv_id":"2401.15050","repositories_listed":0,"syntology":null},{"url":null,"slug":"docgraphlm-documental-graph-language-model","title":"DocGraphLM: Documental Graph Language Model for Information Extraction","date":"2024-01-05","arxiv_id":"2401.02823","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-scaling-up-a-multilingual-vision-and","title":"On Scaling Up a Multilingual Vision and Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"docllm-a-layout-aware-generative-language","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","date":"2023-12-31","arxiv_id":"2401.00908","repositories_listed":0,"syntology":null},{"url":null,"slug":"sljp-semantic-extraction-based-legal-judgment","title":"SLJP: Semantic Extraction based Legal Judgment Prediction","date":"2023-12-13","arxiv_id":"2312.07979","repositories_listed":0,"syntology":null},{"url":null,"slug":"docpedia-unleashing-the-power-of-large","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","date":"2023-11-20","arxiv_id":"2311.11810","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-end-to-end-visual-document","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","date":"2023-11-16","arxiv_id":"2311.09612","repositories_listed":0,"syntology":null},{"url":null,"slug":"donut-hole-donut-sparsification-by-harnessing","title":"DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency","date":"2023-11-09","arxiv_id":"2311.05778","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":"reinforced-ui-instruction-grounding-towards-a","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","date":"2023-10-07","arxiv_id":"2310.04716","repositories_listed":0,"syntology":null},{"url":null,"slug":"protoner-few-shot-incremental-learning-for","title":"ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks","date":"2023-10-03","arxiv_id":"2310.02372","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-pragmatic-differences-between-1","title":"Finding Pragmatic Differences Between Disciplines","date":"2023-09-30","arxiv_id":"2310.00204","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-understanding-for-healthcare","title":"Document Understanding for Healthcare Referrals","date":"2023-09-22","arxiv_id":"2309.13184","repositories_listed":0,"syntology":null},{"url":"/paper/scob-universal-text-understanding-via","slug":"scob-universal-text-understanding-via","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","date":"2023-09-21","arxiv_id":"2309.12382","repositories_listed":0,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scob-universal-text-understanding-via#ran","syntology_url":"https://syntology.ai/paper/2309.12382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12382"}},"official":null}},{"url":null,"slug":"kosmos-2-5-a-multimodal-literate-model","title":"KOSMOS-2.5: A Multimodal Literate Model","date":"2023-09-20","arxiv_id":"2309.11419","repositories_listed":0,"syntology":null},{"url":"/paper/transferdoc-a-self-supervised-transferable","slug":"transferdoc-a-self-supervised-transferable","title":"GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification","date":"2023-09-11","arxiv_id":"2309.05756","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-where-it-matters-rethinking-visual","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","date":"2023-09-03","arxiv_id":"2309.01131","repositories_listed":0,"syntology":null},{"url":null,"slug":"workshop-on-document-intelligence","title":"Workshop on Document Intelligence Understanding","date":"2023-07-31","arxiv_id":"2307.16369","repositories_listed":0,"syntology":null},{"url":null,"slug":"matadoc-margin-and-text-aware-document","title":"MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary","date":"2023-07-24","arxiv_id":"2307.12571","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-and-approach-to-chart-classification","title":"A Survey and Approach to Chart Classification","date":"2023-07-09","arxiv_id":"2307.04147","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-entity-retrieval-with-massive-and","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","date":"2023-06-15","arxiv_id":"2306.08937","repositories_listed":0,"syntology":null},{"url":"/paper/layoutmask-enhance-text-layout-interaction-in","slug":"layoutmask-enhance-text-layout-interaction-in","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","date":"2023-05-30","arxiv_id":"2305.18721","repositories_listed":0,"syntology":null},{"url":null,"slug":"awesome-gpu-memory-constrained-long-document","title":"AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content","date":"2023-05-24","arxiv_id":"2305.14806","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":"fast-structext-an-efficient-hourglass","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","date":"2023-05-19","arxiv_id":"2305.11392","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":"sequence-to-sequence-pre-training-with","title":"Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding","date":"2023-05-16","arxiv_id":"2305.10448","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-6-doc-a-large-scale-multi-format-multi-type","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","date":"2023-05-15","arxiv_id":"2305.08719","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-to-five-truths-in-non-negative-matrix","title":"Two to Five Truths in Non-Negative Matrix Factorization","date":"2023-05-06","arxiv_id":"2305.05389","repositories_listed":0,"syntology":null},{"url":null,"slug":"formnetv2-multimodal-graph-contrastive","title":"FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction","date":"2023-05-04","arxiv_id":"2305.02549","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-table-detection-datasets-for","title":"Revisiting Table Detection Datasets for Visually Rich Documents","date":"2023-05-04","arxiv_id":"2305.04833","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-makes-a-good-dataset-for-symbol","title":"What Makes a Good Dataset for Symbol Description Reading?","date":"2023-04-17","arxiv_id":"2304.08352","repositories_listed":0,"syntology":null},{"url":"/paper/pdf-vqa-a-new-dataset-for-real-world-vqa-on","slug":"pdf-vqa-a-new-dataset-for-real-world-vqa-on","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","date":"2023-04-13","arxiv_id":"2304.06447","repositories_listed":0,"syntology":null},{"url":"/paper/clueweb22-10-billion-web-documents-with-rich","slug":"clueweb22-10-billion-web-documents-with-rich","title":"ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information","date":"2022-11-29","arxiv_id":"2211.15848","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-benchmark-for-structured-extractions-from","title":"VRDU: A Benchmark for Visually-rich Document Understanding","date":"2022-11-15","arxiv_id":"2211.15421","repositories_listed":0,"syntology":null},{"url":null,"slug":"queryform-a-simple-zero-shot-form-entity","title":"QueryForm: A Simple Zero-shot Form Entity Query Framework","date":"2022-11-14","arxiv_id":"2211.07730","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimodal-and-multimodal-representation","title":"Unimodal and Multimodal Representation Training for Relation Extraction","date":"2022-11-11","arxiv_id":"2211.06168","repositories_listed":0,"syntology":null},{"url":"/paper/transformer-based-approach-for-document","slug":"transformer-based-approach-for-document","title":"Transformer-based Approach for Document Understanding","date":"2022-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ernie-mmlayout-multi-grained-multimodal","title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","date":"2022-09-18","arxiv_id":"2209.08569","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-doc-snippet-detection-powering","title":"One-Shot Doc Snippet Detection: Powering Search in Document Beyond Text","date":"2022-09-12","arxiv_id":"2209.06584","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-keyphrase-extraction-with-data","title":"Improving Keyphrase Extraction with Data Augmentation and Information Filtering","date":"2022-09-11","arxiv_id":"2209.04951","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeperdive-the-unreasonable-effectiveness-of","title":"DeeperDive: The Unreasonable Effectiveness of Weak Supervision in Document Understanding A Case Study in Collaboration with UiPath Inc","date":"2022-08-17","arxiv_id":"2208.08000","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-long-documents-with-different","title":"Understanding Long Documents with Different Position-Aware Attentions","date":"2022-08-17","arxiv_id":"2208.08201","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-complex-document-understanding-by","title":"Towards Complex Document Understanding By Discrete Reasoning","date":"2022-07-25","arxiv_id":"2207.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-vldoc-bidirectional-vision-language","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","date":"2022-06-27","arxiv_id":"2206.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-adaptation-for-visual-document","title":"Test-Time Adaptation for Visual Document Understanding","date":"2022-06-15","arxiv_id":"2206.07240","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdu-a-region-based-approach-to-form-style","title":"RDU: A Region-based Approach to Form-style Document Understanding","date":"2022-06-14","arxiv_id":"2206.06890","repositories_listed":0,"syntology":null},{"url":null,"slug":"generation-de-question-a-partir-danalyse","title":"Génération de question à partir d’analyse sémantique pour l’adaptation non supervisée de modèles de compréhension de documents (Question generation from semantic analysis for unsupervised adaptation of document understanding models)","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"matrix-modality-aware-transformer-for","title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","date":"2022-05-17","arxiv_id":"2205.08094","repositories_listed":0,"syntology":null},{"url":null,"slug":"xfund-a-benchmark-dataset-for-multilingual","title":"XFUND: A Benchmark Dataset for Multilingual Visually Rich Form Understanding","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/unified-pretraining-framework-for-document","slug":"unified-pretraining-framework-for-document","title":"Unified Pretraining Framework for Document Understanding","date":"2022-04-22","arxiv_id":"2204.10939","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-text-line-detection-in-historical","title":"Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods","date":"2022-03-23","arxiv_id":"2203.12346","repositories_listed":0,"syntology":null},{"url":null,"slug":"formnet-structural-encoding-beyond-sequential","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","date":"2022-03-16","arxiv_id":"2203.08411","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-bert-for-medical-document","title":"Hierarchical BERT for Medical Document Understanding","date":"2022-03-11","arxiv_id":"2204.09600","repositories_listed":0,"syntology":null},{"url":null,"slug":"webformer-the-web-page-transformer-for","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","date":"2022-02-01","arxiv_id":"2202.00217","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-layout-aware-pretraining-for","title":"Efficient layout-aware pretraining for multimodal form understanding","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lope-learnable-sinusoidal-positional-encoding","title":"LoPE: Learnable Sinusoidal Positional Encoding for Improving Document Transformer Model","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unidoc-unified-pretraining-framework-for","title":"UniDoc: Unified Pretraining Framework for Document Understanding","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"psg-prompt-based-sequence-generation-for","title":"PSG: Prompt-based Sequence Generation for Acronym Extraction","date":"2021-11-29","arxiv_id":"2111.14301","repositories_listed":0,"syntology":null},{"url":null,"slug":"simclad-a-simple-framework-for-contrastive","title":"SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation","date":"2021-11-29","arxiv_id":"2111.14306","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-layout-analysis-with-aesthetic","title":"Document Layout Analysis with Aesthetic-Guided Image Augmentation","date":"2021-11-27","arxiv_id":"2111.13809","repositories_listed":0,"syntology":null},{"url":null,"slug":"handling-tree-structured-text-parsing","title":"Handling tree-structured text: parsing directory pages","date":"2021-11-24","arxiv_id":"2111.12317","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-position-aware-attention-mechanism-in","title":"Probing Position-Aware Attention Mechanism in Long Document Understanding","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"opad-an-optimized-policy-based-active","title":"OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis","date":"2021-10-01","arxiv_id":"2110.02069","repositories_listed":0,"syntology":null},{"url":null,"slug":"position-masking-for-improved-layout-aware","title":"Position Masking for Improved Layout-Aware Document Understanding","date":"2021-09-01","arxiv_id":"2109.00442","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-law-of-large-documents-understanding-the","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","date":"2021-07-16","arxiv_id":"2107.08128","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-domain-agnostic-and-specific","title":"Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation","date":"2021-07-01","arxiv_id":"2107.00316","repositories_listed":0,"syntology":null},{"url":"/paper/document-collection-visual-question-answering","slug":"document-collection-visual-question-answering","title":"Document Collection Visual Question Answering","date":"2021-04-27","arxiv_id":"2104.14336","repositories_listed":0,"syntology":null},{"url":null,"slug":"lampret-layout-aware-multimodal-pretraining","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","date":"2021-04-16","arxiv_id":"2104.08405","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-knowledge-extraction-with-human","title":"Automatic Knowledge Extraction with Human Interface","date":"2021-04-09","arxiv_id":"2104.04415","repositories_listed":0,"syntology":null},{"url":null,"slug":"decontextualization-making-sentences-stand","title":"Decontextualization: Making Sentences Stand-Alone","date":"2021-02-09","arxiv_id":"2102.05169","repositories_listed":0,"syntology":null},{"url":null,"slug":"at-bert-adversarial-training-bert-for-acronym","title":"AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21","date":"2021-01-11","arxiv_id":"2101.03700","repositories_listed":0,"syntology":null},{"url":null,"slug":"bros-a-pre-trained-language-model-for","title":"BROS: A Pre-trained Language Model for Understanding Texts in Document","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acronym-identification-and-disambiguation","title":"Acronym Identification and Disambiguation Shared Tasks for Scientific Document Understanding","date":"2020-12-22","arxiv_id":"2012.11760","repositories_listed":0,"syntology":null},{"url":null,"slug":"merge-and-recognize-a-geometry-and-2d-context","title":"Merge and Recognize: A Geometry and 2D Context Aware Graph Model for Named Entity Recognition from Visual Documents","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"friendly-topic-assistant-for-transformer","title":"Friendly Topic Assistant for Transformer Based Abstractive Summarization","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-graph-neural-network-with","title":"Attention-Based Graph Neural Network with Global Context Awareness for Document Understanding","date":"2020-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-gpt-with-congruent-transformers","title":"Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models","date":"2020-09-18","arxiv_id":"2009.08636","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-information-extraction-from-text","title":"Multi-modal Information Extraction from Text, Semi-structured, and Tabular Data on the Web","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-cross-lingual-pivots-to-model","title":"Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation","date":"2020-06-16","arxiv_id":"2006.08881","repositories_listed":0,"syntology":null},{"url":null,"slug":"table-structure-extraction-with-bi","title":"Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks","date":"2020-01-08","arxiv_id":"2001.02501","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-al-bert-for-arbitrarily-long-document","title":"BERT-AL: BERT for Arbitrarily Long Document Understanding","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"table-of-contents-generation-on-contemporary","title":"Table-Of-Contents generation on contemporary documents","date":"2019-11-20","arxiv_id":"1911.08836","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-retrospective-recount-of-computer","title":"A Retrospective Recount of Computer Architecture Research with a Data-Driven Study of Over Four Decades of ISCA Publications","date":"2019-06-22","arxiv_id":"1906.09380","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-user-centered-concept-mining-system-for","title":"A User-Centered Concept Mining System for Query and Document Understanding at Tencent","date":"2019-05-21","arxiv_id":"1905.08487","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-convolution-for-multimodal-information","title":"Graph Convolution for Multimodal Information Extraction from Visually Rich Documents","date":"2019-03-27","arxiv_id":"1903.11279","repositories_listed":0,"syntology":null}],"record_sha256":"e96b24a99ffbeefc969425d03b0ca8bcda9fd48a0b1530ab39537c72e93f102f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}