{"id":15176705,"url":"https://github.com/stickeritis/sticker","last_synced_at":"2025-10-01T16:30:31.172Z","repository":{"id":53688705,"uuid":"170839025","full_name":"stickeritis/sticker","owner":"stickeritis","description":"Succeeded by SyntaxDot: https://github.com/tensordot/syntaxdot","archived":true,"fork":false,"pushed_at":"2021-03-19T10:08:03.000Z","size":1189,"stargazers_count":25,"open_issues_count":15,"forks_count":2,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-04-21T20:38:05.484Z","etag":null,"topics":["dependency-parsing","dilated-convolution","finalfusion","lstm","part-of-speech-tagger","rust","tensorflow","topological-fields","transformer"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/stickeritis.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null}},"created_at":"2019-02-15T09:35:54.000Z","updated_at":"2023-06-04T22:02:12.000Z","dependencies_parsed_at":"2022-08-27T01:40:50.226Z","dependency_job_id":null,"html_url":"https://github.com/stickeritis/sticker","commit_stats":null,"previous_names":["danieldk/sticker"],"tags_count":17,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stickeritis%2Fsticker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stickeritis%2Fsticker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stickeritis%2Fsticker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stickeritis%2Fsticker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/stickeritis","download_url":"https://codeload.github.com/stickeritis/sticker/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234882550,"owners_count":18901290,"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","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":["dependency-parsing","dilated-convolution","finalfusion","lstm","part-of-speech-tagger","rust","tensorflow","topological-fields","transformer"],"created_at":"2024-09-27T13:40:29.071Z","updated_at":"2025-10-01T16:30:30.723Z","avatar_url":"https://github.com/stickeritis.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"**Warning:** sticker is succeeded by\n[SyntaxDot](https://github.com/tensordot/syntaxdot), which supports\n*many* new features:\n\n* Multi-task learning.\n* Pretrained transformer models, suchs as BERT and XLM-R.\n* Biaffine parsing in addition to parsing as sequence labeling.\n* Lemmatization.\n\n# sticker\n\n**sticker** is a sequence labeler using neural networks.\n\n## Introduction\n\nsticker is a sequence labeler that uses either recurrent neural\nnetworks, transformers, or dilated convolution networks. In principle,\nit can be used to perform any sequence labeling task, but so far the\nfocus has been on:\n\n* Part-of-speech tagging\n* Topological field tagging\n* Dependency parsing\n* Named entity recognition\n\n## Features\n\n* Input representations:\n  * [finalfusion](https://finalfusion.github.io/) embeddings with subword units\n  * Bidirectional byte LSTMs\n* Hidden representations:\n  * Bidirectional recurrent neural networks (LSTM or GRU)\n  * Transformers\n  * Dillated convolutions\n* Classification layers:\n  * Softmax (best-N)\n  * CRF\n* Deployment:\n  * Standalone binary that links against `libtensorflow`\n  * Very liberal [license](LICENSE.md)\n  * Docker containers with models\n\n## Status\n\nsticker is almost production-ready and we are preparing for release\n1.0.0. Graphs and models crated with the current version **must** work\nwith sticker 1.x.y. There may still be breaking API or configuration\nfile changes until 1.0.0 is released.\n\n## Where to go from here\n\n* [Installing sticker](doc/INSTALL.md)\n* [Pretrained models](doc/PRETRAINED.md)\n* [Using sticker](doc/USAGE.md)\n* [Training a sticker model](doc/TRAIN.md)\n\n## References\n\nsticker uses techniques from or was inspired by the following papers:\n\n* [Finding Function in Form: Compositional Character Models for Open\n  Vocabulary Word\n  Representation](https://aclweb.org/anthology/papers/D/D15/D15-1176/). Wang\n  Ling, Chris Dyer, Alan W Black, Isabel Trancoso, Ramón Fermandez,\n  Silvio Amir, Luís Marujo, Tiago Luís, 2015, Proceedings of the 2015\n  Conference on Empirical Methods in Natural Language Processing\n* [Transition-based dependency parsing with topological\n  fields](https://aclweb.org/anthology/papers/P/P16/P16-2001/). Daniël\n  de Kok, Erhard Hinrichs, 2016, Proceedings of the 54th Annual\n  Meeting of the Association for Computational Linguistics\n* [Viable Dependency Parsing as Sequence\n  Labeling](https://www.aclweb.org/anthology/papers/N/N19/N19-1077/). Michalina\n  Strzyz, David Vilares, Carlos Gómez-Rodríguez, 2019, Proceedings of\n  the 2019 Conference of the North American Chapter of the Association\n  for Computational Linguistics: Human Language Technologies\n\n## Issues\n\nYou can report bugs and feature requests in the [sticker issue\ntracker](https://github.com/stickeritis/sticker/issues).\n\n## License\n\nsticker is licensed under the [Blue Oak Model License version\n1.0.0](LICENSE.md). The Tensorflow protocol buffer definitions in\n`tf-proto` are licensed under the Apache License version 2.0. The\n[list of contributors](CONTRIBUTORS) is also available.\n\n## Credits\n\n* sticker is developed by Daniël de Kok \u0026 Tobias Pütz.\n* The Python precursor to sticker was developer by Erik Schill.\n* Sebastian Pütz and Patricia Fischer reviewed a lot of code across\n  the sticker projects.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstickeritis%2Fsticker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstickeritis%2Fsticker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstickeritis%2Fsticker/lists"}