{"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/text-segmentation","name":"Text Segmentation","slug":"text-segmentation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":124,"papers_with_code":40,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/conll-1","name":"CoNLL","full_name":"","num_papers_in_archive":187},{"url":"/dataset/spmrl-hebrew-segmentation-data","name":"SPMRL Hebrew segmentation data","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ytseg","name":"YTSeg","full_name":"","num_papers_in_archive":2},{"url":"/dataset/careercoach-2022","name":"CareerCoach 2022","full_name":"","num_papers_in_archive":1},{"url":"/dataset/conll-2017-shared-task-automatically","name":"CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings","full_name":"","num_papers_in_archive":1},{"url":"/dataset/urdudoc","name":"UrduDoc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wiki5k-hebrew-segmentation","name":"Wiki5K Hebrew segmentation","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":124,"of_with_code":40,"tagged_in_all":124,"counts":{"archive_papers_tagged":124,"with_a_code_link":40,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":124,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/cotype-joint-extraction-of-typed-entities-and","slug":"cotype-joint-extraction-of-typed-entities-and","title":"CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases","date":"2016-10-27","arxiv_id":"1610.08763","repositories_listed":3,"syntology":null},{"url":"/paper/segmenting-text-and-learning-their-rewards","slug":"segmenting-text-and-learning-their-rewards","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","date":"2025-01-06","arxiv_id":"2501.02790","repositories_listed":2,"syntology":null},{"url":"/paper/wenetspeech-a-10000-hours-multi-domain","slug":"wenetspeech-a-10000-hours-multi-domain","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","date":"2021-10-07","arxiv_id":"2110.03370","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wenetspeech-a-10000-hours-multi-domain#ran","syntology_url":"https://syntology.ai/paper/2110.03370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03370"}},"official":{"repos":["wenet-e2e/wenetspeech"],"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":["listed","official"]}}},{"url":"/paper/text-segmentation-as-a-supervised-learning","slug":"text-segmentation-as-a-supervised-learning","title":"Text Segmentation as a Supervised Learning Task","date":"2018-03-25","arxiv_id":"1803.09337","repositories_listed":2,"syntology":null},{"url":"/paper/sequence-modeling-via-segmentations","slug":"sequence-modeling-via-segmentations","title":"Sequence Modeling via Segmentations","date":"2017-02-24","arxiv_id":"1702.07463","repositories_listed":2,"syntology":null},{"url":"/paper/controltext-unlocking-controllable-fonts-in","slug":"controltext-unlocking-controllable-fonts-in","title":"ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations","date":"2025-02-16","arxiv_id":"2502.10999","repositories_listed":1,"syntology":null},{"url":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-chunking-learning-efficient-text#ran","syntology_url":"https://syntology.ai/paper/2410.12788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12788"}},"official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/was-dataset-and-methods-for-artistic-text","slug":"was-dataset-and-methods-for-artistic-text","title":"WAS: Dataset and Methods for Artistic Text Segmentation","date":"2024-07-31","arxiv_id":"2408.00106","repositories_listed":1,"syntology":null},{"url":"/paper/eaformer-scene-text-segmentation-with-edge","slug":"eaformer-scene-text-segmentation-with-edge","title":"EAFormer: Scene Text Segmentation with Edge-Aware Transformers","date":"2024-07-24","arxiv_id":"2407.17020","repositories_listed":1,"syntology":null},{"url":"/paper/towards-detecting-ai-generated-text-within","slug":"towards-detecting-ai-generated-text-within","title":"Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights","date":"2024-03-06","arxiv_id":"2403.03506","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/towards-detecting-ai-generated-text-within#ran","syntology_url":"https://syntology.ai/paper/2403.03506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03506"}},"official":{"repos":["douglashiwo/aisentencedetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/hi-sam-marrying-segment-anything-model-for","slug":"hi-sam-marrying-segment-anything-model-for","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","date":"2024-01-31","arxiv_id":"2401.17904","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hi-sam-marrying-segment-anything-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.17904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17904"}},"official":{"repos":["ymy-k/hi-sam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/filtered-semi-markov-crf","slug":"filtered-semi-markov-crf","title":"Filtered Semi-Markov CRF","date":"2023-11-29","arxiv_id":"2311.18028","repositories_listed":1,"syntology":null},{"url":"/paper/psstrnet-progressive-segmentation-guided","slug":"psstrnet-progressive-segmentation-guided","title":"PSSTRNet: Progressive Segmentation-guided Scene Text Removal Network","date":"2023-06-13","arxiv_id":"2306.07842","repositories_listed":1,"syntology":null},{"url":"/paper/expanding-scope-adapting-english-adversarial","slug":"expanding-scope-adapting-english-adversarial","title":"Expanding Scope: Adapting English Adversarial Attacks to Chinese","date":"2023-06-08","arxiv_id":"2306.04874","repositories_listed":1,"syntology":null},{"url":"/paper/ccdwt-gan-generative-adversarial-networks","slug":"ccdwt-gan-generative-adversarial-networks","title":"CCDWT-GAN: Generative Adversarial Networks Based on Color Channel Using Discrete Wavelet Transform for Document Image Binarization","date":"2023-05-27","arxiv_id":"2305.17420","repositories_listed":1,"syntology":null},{"url":"/paper/three-stage-binarization-of-color-document","slug":"three-stage-binarization-of-color-document","title":"Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks","date":"2022-11-29","arxiv_id":"2211.16098","repositories_listed":1,"syntology":null},{"url":"/paper/dq-detr-dual-query-detection-transformer-for","slug":"dq-detr-dual-query-detection-transformer-for","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","date":"2022-11-28","arxiv_id":"2211.15516","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-character-to-character","slug":"self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","arxiv_id":"2211.00288","repositories_listed":1,"syntology":null},{"url":"/paper/toward-unifying-text-segmentation-and-long","slug":"toward-unifying-text-segmentation-and-long","title":"Toward Unifying Text Segmentation and Long Document Summarization","date":"2022-10-28","arxiv_id":"2210.16422","repositories_listed":1,"syntology":null},{"url":"/paper/a-glyph-driven-topology-enhancement-network","slug":"a-glyph-driven-topology-enhancement-network","title":"Self-supervised Implicit Glyph Attention for Text Recognition","date":"2022-03-07","arxiv_id":"2203.03382","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-discourse-segmentation-for","slug":"weakly-supervised-discourse-segmentation-for","title":"Weakly supervised discourse segmentation for multiparty oral conversations","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sefamerve-arge-at-semeval-2021-task-5-toxic","slug":"sefamerve-arge-at-semeval-2021-task-5-toxic","title":"Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-sequence-segmentation-as-determining","slug":"neural-sequence-segmentation-as-determining","title":"Neural Sequence Segmentation as Determining the Leftmost Segments","date":"2021-04-15","arxiv_id":"2104.07217","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"6 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/neural-sequence-segmentation-as-determining#ran","syntology_url":"https://syntology.ai/paper/2104.07217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07217"}},"official":{"repos":["LeePleased/LeftmostSeg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/topical-change-detection-in-documents-via","slug":"topical-change-detection-in-documents-via","title":"Structural Text Segmentation of Legal Documents","date":"2020-12-07","arxiv_id":"2012.03619","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-text-segmentation-for-medieval","slug":"hierarchical-text-segmentation-for-medieval","title":"Hierarchical Text Segmentation for Medieval Manuscripts","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-text-segmentation-a-novel-dataset","slug":"rethinking-text-segmentation-a-novel-dataset","title":"Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach","date":"2020-11-27","arxiv_id":"2011.14021","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-natural-language-segmentation","slug":"interpretable-natural-language-segmentation","title":"Interpretable Natural Language Segmentation Based on Link Grammar","date":"2020-11-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chapter-captor-text-segmentation-in-novels","slug":"chapter-captor-text-segmentation-in-novels","title":"Chapter Captor: Text Segmentation in Novels","date":"2020-11-09","arxiv_id":"2011.04163","repositories_listed":1,"syntology":null},{"url":"/paper/improving-segmentation-for-technical-support","slug":"improving-segmentation-for-technical-support","title":"Improving Segmentation for Technical Support Problems","date":"2020-05-22","arxiv_id":"2005.11055","repositories_listed":1,"syntology":null},{"url":"/paper/text-segmentation-by-cross-segment-attention","slug":"text-segmentation-by-cross-segment-attention","title":"Text Segmentation by Cross Segment Attention","date":"2020-04-30","arxiv_id":"2004.14535","repositories_listed":1,"syntology":null},{"url":"/paper/two-level-transformer-and-auxiliary-coherence","slug":"two-level-transformer-and-auxiliary-coherence","title":"Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation","date":"2020-01-03","arxiv_id":"2001.00891","repositories_listed":1,"syntology":null},{"url":"/paper/crowdsourcing-and-aggregating-nested-markable","slug":"crowdsourcing-and-aggregating-nested-markable","title":"Crowdsourcing and Aggregating Nested Markable Annotations","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/handwritten-text-segmentation-via-end-to-end","slug":"handwritten-text-segmentation-via-end-to-end","title":"Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network","date":"2019-06-12","arxiv_id":"1906.05229","repositories_listed":1,"syntology":null},{"url":"/paper/attention-based-neural-text-segmentation","slug":"attention-based-neural-text-segmentation","title":"Attention-based Neural Text Segmentation","date":"2018-08-29","arxiv_id":"1808.09935","repositories_listed":1,"syntology":null},{"url":"/paper/a-characterwise-windowed-approach-to-hebrew","slug":"a-characterwise-windowed-approach-to-hebrew","title":"A Characterwise Windowed Approach to Hebrew Morphological Segmentation","date":"2018-08-22","arxiv_id":"1808.07214","repositories_listed":1,"syntology":null},{"url":"/paper/c-hts-a-concept-based-hierarchical-text","slug":"c-hts-a-concept-based-hierarchical-text","title":"C-HTS: A Concept-based Hierarchical Text Segmentation approach","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-text-segmentation-using-semantic","slug":"unsupervised-text-segmentation-using-semantic","title":"Unsupervised Text Segmentation Using Semantic Relatedness Graphs","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-way-for-segmentation-of-bangla","slug":"an-efficient-way-for-segmentation-of-bangla","title":"An efficient way for segmentation of Bangla characters in printed document using curved scanning","date":"2016-05-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/khmer-word-segmentation-using-conditional","slug":"khmer-word-segmentation-using-conditional","title":"Khmer Word Segmentation Using Conditional Random Fields","date":"2015-10-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/text-segmentation-based-on-semantic-word","slug":"text-segmentation-based-on-semantic-word","title":"Text Segmentation based on Semantic Word Embeddings","date":"2015-03-18","arxiv_id":"1503.05543","repositories_listed":1,"syntology":null},{"url":null,"slug":"the-impact-of-fine-tuning-in-llama-on","title":"The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation","date":"2025-06-10","arxiv_id":"2506.08827","repositories_listed":0,"syntology":null},{"url":null,"slug":"bp-seg-a-graphical-model-approach-to","title":"BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation","date":"2025-05-22","arxiv_id":"2505.16965","repositories_listed":0,"syntology":null},{"url":null,"slug":"br-taxqa-r-a-dataset-for-question-answering","title":"BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law","date":"2025-05-21","arxiv_id":"2505.15916","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsal-few-shot-text-segmentation-based-on","title":"TSAL: Few-shot Text Segmentation Based on Attribute Learning","date":"2025-04-15","arxiv_id":"2504.11164","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-context-driven-training-free-network-for","title":"A Context-Driven Training-Free Network for Lightweight Scene Text Segmentation and Recognition","date":"2025-03-19","arxiv_id":"2503.15639","repositories_listed":0,"syntology":null},{"url":null,"slug":"posta-a-go-to-framework-for-customized","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation","date":"2025-03-19","arxiv_id":"2503.14908","repositories_listed":0,"syntology":null},{"url":null,"slug":"docsam-unified-document-image-segmentation","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"char-sam-turning-segment-anything-model-into","title":"Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts","date":"2024-12-27","arxiv_id":"2412.19917","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-level-diffusion-a-framework-for","title":"Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models","date":"2024-12-15","arxiv_id":"2412.11333","repositories_listed":0,"syntology":null},{"url":null,"slug":"rose-revolutionizing-open-set-dense","title":"ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model","date":"2024-11-29","arxiv_id":"2412.00153","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-trends-in-linear-text-segmentation-a","title":"Recent Trends in Linear Text Segmentation: a Survey","date":"2024-11-25","arxiv_id":"2411.16613","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-question-answering-precision-with","title":"Enhancing Question Answering Precision with Optimized Vector Retrieval and Instructions","date":"2024-11-01","arxiv_id":"2411.01039","repositories_listed":0,"syntology":null},{"url":"/paper/eeg-language-modeling-for-pathology-detection","slug":"eeg-language-modeling-for-pathology-detection","title":"EEG-Language Modeling for Pathology Detection","date":"2024-09-02","arxiv_id":"2409.07480","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/eeg-language-modeling-for-pathology-detection#ran","syntology_url":"https://syntology.ai/paper/2409.07480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07480"}},"official":null}},{"url":null,"slug":"tocbert-medical-document-structure-extraction","title":"TocBERT: Medical Document Structure Extraction Using Bidirectional Transformers","date":"2024-06-27","arxiv_id":"2406.19526","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-easy-read-text-segmentation","title":"Automating Easy Read Text Segmentation","date":"2024-06-17","arxiv_id":"2406.11464","repositories_listed":0,"syntology":null},{"url":null,"slug":"proofread-fixes-all-errors-with-one-tap","title":"Proofread: Fixes All Errors with One Tap","date":"2024-06-06","arxiv_id":"2406.04523","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-generation-with-knowledge","title":"Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering","date":"2024-04-26","arxiv_id":"2404.17723","repositories_listed":0,"syntology":null},{"url":"/paper/from-text-segmentation-to-smart-chaptering-a","slug":"from-text-segmentation-to-smart-chaptering-a","title":"From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions","date":"2024-02-27","arxiv_id":"2402.17633","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reliable-knowledge-processing-framework-for","title":"A Reliable Knowledge Processing Framework for Combustion Science using Foundation Models","date":"2023-12-31","arxiv_id":"2401.00544","repositories_listed":0,"syntology":null},{"url":null,"slug":"segmenting-messy-text-detecting-boundaries-in","title":"Segmenting Messy Text: Detecting Boundaries in Text Derived from Historical Newspaper Images","date":"2023-12-20","arxiv_id":"2312.12773","repositories_listed":0,"syntology":null},{"url":null,"slug":"upocr-towards-unified-pixel-level-ocr","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","date":"2023-12-05","arxiv_id":"2312.02694","repositories_listed":0,"syntology":null},{"url":null,"slug":"anylens-a-generative-diffusion-model-with-any","title":"Curved Diffusion: A Generative Model With Optical Geometry Control","date":"2023-11-29","arxiv_id":"2311.17609","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-scene-text-segmentation-with","title":"Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions","date":"2023-08-25","arxiv_id":"2308.13178","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-sentence-embedding","title":"A Comparative Study of Sentence Embedding Models for Assessing Semantic Variation","date":"2023-08-08","arxiv_id":"2308.04625","repositories_listed":0,"syntology":null},{"url":null,"slug":"handwritten-and-printed-text-segmentation-a","title":"Handwritten and Printed Text Segmentation: A Signature Case Study","date":"2023-07-15","arxiv_id":"2307.07887","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-text-instance-segmentation","title":"Weakly-Supervised Text Instance Segmentation","date":"2023-03-20","arxiv_id":"2303.10848","repositories_listed":0,"syntology":null},{"url":"/paper/document-summarization-with-text-segmentation","slug":"document-summarization-with-text-segmentation","title":"Document Summarization with Text Segmentation","date":"2023-01-20","arxiv_id":"2301.08817","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-summarization-unified-text","title":"Structured Summarization: Unified Text Segmentation and Segment Labeling as a Generation Task","date":"2022-09-28","arxiv_id":"2209.13759","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-for-tiff-compressed-document-images","title":"OCR for TIFF Compressed Document Images Directly in Compressed Domain Using Text segmentation and Hidden Markov Model","date":"2022-09-13","arxiv_id":"2209.09118","repositories_listed":0,"syntology":null},{"url":null,"slug":"dp-parse-finding-word-boundaries-from-raw","title":"DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon","date":"2022-06-22","arxiv_id":"2206.11332","repositories_listed":0,"syntology":null},{"url":"/paper/unsupervised-tokenization-learning","slug":"unsupervised-tokenization-learning","title":"Unsupervised Tokenization Learning","date":"2022-05-23","arxiv_id":"2205.11443","repositories_listed":0,"syntology":{"n":23,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/unsupervised-tokenization-learning#ran","syntology_url":"https://syntology.ai/paper/2205.11443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11443"}},"official":null}},{"url":null,"slug":"an-empirical-study-of-ctc-based-models-for","title":"Towards Deployable OCR models for Indic languages","date":"2022-05-13","arxiv_id":"2205.06740","repositories_listed":0,"syntology":null},{"url":null,"slug":"topwords-seg-simultaneous-text-segmentation","title":"TopWORDS-Seg: Simultaneous Text Segmentation and Word Discovery for Open-Domain Chinese Texts via Bayesian Inference","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzy-segmentations-of-a-string","title":"Fuzzy Segmentations of a String","date":"2022-01-31","arxiv_id":"2201.13427","repositories_listed":0,"syntology":null},{"url":null,"slug":"bts-a-bi-lingual-benchmark-for-text","title":"BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-over-pre-trained-transformer-for","title":"Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence","date":"2021-10-14","arxiv_id":"2110.07160","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-constraints-and-descriptive","title":"Learning Constraints and Descriptive Segmentation for Subevent Detection","date":"2021-09-13","arxiv_id":"2109.06316","repositories_listed":0,"syntology":null},{"url":null,"slug":"kits-iwslt-2021-offline-speech-translation","title":"KIT’s IWSLT 2021 Offline Speech Translation System","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-data-driven-subword-modeling-for-end","title":"Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition","date":"2021-04-19","arxiv_id":"2104.09106","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-and-domain-adaptation-for-supervised","title":"Training and Domain Adaptation for Supervised Text Segmentation","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"highly-fast-text-segmentation-with-pairwise","title":"Highly Fast Text Segmentation With Pairwise Markov Chains","date":"2021-02-17","arxiv_id":"2102.11037","repositories_listed":0,"syntology":null},{"url":null,"slug":"german-arabic-speech-to-speech-translation","title":"German-Arabic Speech-to-Speech Translation for Psychiatric Diagnosis","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-html-in-free-text-web-named-entity","title":"Leveraging HTML in Free Text Web Named Entity Recognition","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bats-a-spectral-biclustering-approach-to","title":"BATS: A Spectral Biclustering Approach to Single Document Topic Modeling and Segmentation","date":"2020-08-05","arxiv_id":"2008.02218","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-model-for-document-segmentation-and","title":"A Joint Model for Document Segmentation and Segment Labeling","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-de-texte-non-supervis-ee-pour-la","title":"Segmentation de texte non-supervis\\'ee pour la d\\'etection de th\\'ematiques \\`a l'aide de plongements lexicaux (Unsupervised text segmentation for topic detection using embeddings )","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sanskrit-segmentation-revisited","title":"Sanskrit Segmentation Revisited","date":"2020-05-13","arxiv_id":"2005.06383","repositories_listed":0,"syntology":null},{"url":null,"slug":"books-of-hours-the-first-liturgical-data-set","title":"Books of Hours. the First Liturgical Data Set for Text Segmentation.","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weak-supervision-for-generating-pixel-level","title":"Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation","date":"2019-11-19","arxiv_id":"1911.09026","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cascade-model-for-proposition-extraction-in","title":"A Cascade Model for Proposition Extraction in Argumentation","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-bayesian-natural-language-processing","title":"Deep Bayesian Natural Language Processing","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-using-n-grams-to-annotate","title":"Text Segmentation Using N-grams to Annotate Hadith Corpus","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"une-approche-hybride-pour-la-segmentation","title":"Une approche hybride pour la segmentation automatique de documents juridiques (A hybrid approach for automatic text segmentation)","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-segmentation-on-multilabel-documents-a","title":"Text segmentation on multilabel documents: A distant-supervised approach","date":"2019-04-14","arxiv_id":"1904.06730","repositories_listed":0,"syntology":null},{"url":null,"slug":"coco_ts-dataset-pixel-level-annotations-based","title":"COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation","date":"2019-04-01","arxiv_id":"1904.00818","repositories_listed":0,"syntology":null},{"url":null,"slug":"curve-text-detection-with-local-segmentation","title":"Detecting Curve Text with Local Segmentation Network and Curve Connection","date":"2019-03-23","arxiv_id":"1903.09837","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-extraction-of-indic-regional-language","title":"Offline Extraction of Indic Regional Language from Natural Scene Image using Text Segmentation and Deep Convolutional Sequence","date":"2018-06-16","arxiv_id":"1806.06208","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-the-most-dominant-event-in-a-news","title":"Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"information-bottleneck-inspired-method-for","title":"Information Bottleneck Inspired Method For Chat Text Segmentation","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/fused-text-segmentation-networks-for-multi","slug":"fused-text-segmentation-networks-for-multi","title":"Fused Text Segmentation Networks for Multi-oriented Scene Text Detection","date":"2017-09-11","arxiv_id":"1709.03272","repositories_listed":0,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/text-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/text-segmentation/papers/2","json":"/task/text-segmentation/papers/2.json","rows":24},{"order":"ran","page":1,"of":1,"url":"/task/text-segmentation/papers/ran/1","json":"/task/text-segmentation/papers/ran/1.json","rows":7}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"d7ee719fd541fd5515e94cc787ad9da54d706d8692e4b548b92a6963d289fddb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}