{"id":33058336,"url":"https://github.com/dhlab-epfl/LinkedBooksDeepReferenceParsing","last_synced_at":"2025-11-23T16:01:15.955Z","repository":{"id":71992153,"uuid":"119896321","full_name":"dhlab-epfl/LinkedBooksDeepReferenceParsing","owner":"dhlab-epfl","description":"A deep learning architecture for reference mining from literature in the arts and humanities.","archived":false,"fork":false,"pushed_at":"2019-08-14T09:56:26.000Z","size":5711,"stargazers_count":14,"open_issues_count":2,"forks_count":4,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-06-11T03:33:56.621Z","etag":null,"topics":["annotated-references","annotations","annotations-dataset","citations","crf","crf-model","dataset","deep-learning","footnotes","venice"],"latest_commit_sha":null,"homepage":"https://www.frontiersin.org/articles/10.3389/frma.2018.00021/full","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dhlab-epfl.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-02-01T21:33:24.000Z","updated_at":"2024-03-12T04:53:15.000Z","dependencies_parsed_at":"2024-01-14T05:10:05.087Z","dependency_job_id":null,"html_url":"https://github.com/dhlab-epfl/LinkedBooksDeepReferenceParsing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dhlab-epfl/LinkedBooksDeepReferenceParsing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhlab-epfl%2FLinkedBooksDeepReferenceParsing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhlab-epfl%2FLinkedBooksDeepReferenceParsing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhlab-epfl%2FLinkedBooksDeepReferenceParsing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhlab-epfl%2FLinkedBooksDeepReferenceParsing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dhlab-epfl","download_url":"https://codeload.github.com/dhlab-epfl/LinkedBooksDeepReferenceParsing/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dhlab-epfl%2FLinkedBooksDeepReferenceParsing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":285977076,"owners_count":27264304,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-11-23T02:00:06.149Z","response_time":135,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["annotated-references","annotations","annotations-dataset","citations","crf","crf-model","dataset","deep-learning","footnotes","venice"],"created_at":"2025-11-14T05:00:28.824Z","updated_at":"2025-11-23T16:01:15.910Z","avatar_url":"https://github.com/dhlab-epfl.png","language":"Jupyter Notebook","funding_links":[],"categories":["Information Extraction and NLP"],"sub_categories":[],"readme":"# Deep Reference Parsing\n\nThis repository contains the code for the following article:\n    \n    @article{alves_deep_2018,\n          author       = {{Rodrigues Alves, Danny and Giovanni Colavizza and Frédéric Kaplan}},\n          title        = {{Deep Reference Mining from Scholarly Literature in the Arts and Humanities}},\n          journal      = {{Frontiers in Research Metrics \u0026 Analytics}},\n          volume       = 3,\n          number       = 21,\n          year         = 2018,\n          doi          = {10.3389/frma.2018.00021}\n        }\n\n## Task definition\n\nWe focus on the task of reference mining, instantiated into three tasks: reference components detection (task 1), reference typology detection (task 2) and reference span detection (task 3).\n\n* Sequence: *G. Ostrogorsky, History of the Byzantine State, Rutgers University Press, 1986.*\n* Task 1: *author author title title title title title publisher publisher publisher year*\n* Task 2: *b-secondary i-secondary ... e-secondary*\n* Task 3: *b-r i-r ... e-r*\n\n## Contents\n\n* `LICENSE` MIT.\n* `README.md` this file.\n* `dataset/`\n    * [train](dataset/clean_test.txt) Train split, CoNLL format.\n    * [test](dataset/clean_train.txt) Test split, CoNLL format.\n    * [validation](dataset/clean_valid.txt) Validation split, CoNLL format.\n* [compressed dataset](dataset.tar.gz) Compressed dataset.\n* [data facts](Data%20Facts.ipynb) a Python notebook to explore the dataset (number of references, tag distributions).\n* [crf_baseline](crf_baseline) CRF baseline implementation details.\n* [keras](keras) Keras implementation details.\n* [tensorflow](tensorflow) TF implementation details.\n\n## Dataset\n\nExample of dataset entry (beginning of validation dataset, first line/sequence): Token Task1tag Task2tag Task3tag`:\n\n    -DOCSTART- -X- -X- o\n\n    C author b-secondary b-r\n    . author i-secondary i-r\n    Agnoletti author i-secondary i-r\n    , author i-secondary i-r\n    Treviso title i-secondary i-r\n    e title i-secondary i-r\n    le title i-secondary i-r\n    sue title i-secondary i-r\n    pievi title i-secondary i-r\n    . title i-secondary i-r\n    Illustrazione title i-secondary i-r\n    storica title i-secondary i-r\n    , title i-secondary i-r\n    Treviso publicationplace i-secondary i-r\n    1898 year i-secondary i-r\n    , year i-secondary i-r\n    2 publicationspecifications i-secondary i-r\n    v publicationspecifications e-secondary i-r\n    . publicationspecifications e-secondary e-r\n\nPre-trained word vectors can be downloaded from Zenodo: [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.1175213.svg)](https://doi.org/10.5281/zenodo.1175213)\n\n## Implementations\n\n### CRF baseline\n\nSee internal [readme](crf_baseline/README.md) for details.\n\n### Keras\n\nSee internal [readme](keras/README.md) for details.\n\n### Tensor Flow\n\nSee internal [readme](tensorflow/README.md) for details.\n\nThis implementation borrows from [Guillaume Genthial's Sequence Tagging with Tensorflow](https://guillaumegenthial.github.io/sequence-tagging-with-tensorflow.html).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdhlab-epfl%2FLinkedBooksDeepReferenceParsing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdhlab-epfl%2FLinkedBooksDeepReferenceParsing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdhlab-epfl%2FLinkedBooksDeepReferenceParsing/lists"}