{"id":28795730,"url":"https://github.com/ukplab/coling2016-pcrf-seq2seq","last_synced_at":"2025-09-14T18:46:40.138Z","repository":{"id":66147358,"uuid":"70487349","full_name":"UKPLab/coling2016-pcrf-seq2seq","owner":"UKPLab","description":"An adaptation of MarMot morphological tagger for generic sequence-to-sequence tasks","archived":false,"fork":false,"pushed_at":"2019-12-29T14:17:25.000Z","size":33,"stargazers_count":10,"open_issues_count":2,"forks_count":3,"subscribers_count":29,"default_branch":"master","last_synced_at":"2025-06-18T03:10:03.977Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/UKPLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2016-10-10T12:52:29.000Z","updated_at":"2025-01-17T13:16:47.000Z","dependencies_parsed_at":"2023-03-10T23:40:00.330Z","dependency_job_id":null,"html_url":"https://github.com/UKPLab/coling2016-pcrf-seq2seq","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/UKPLab/coling2016-pcrf-seq2seq","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fcoling2016-pcrf-seq2seq","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fcoling2016-pcrf-seq2seq/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fcoling2016-pcrf-seq2seq/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fcoling2016-pcrf-seq2seq/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UKPLab","download_url":"https://codeload.github.com/UKPLab/coling2016-pcrf-seq2seq/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fcoling2016-pcrf-seq2seq/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275151340,"owners_count":25414441,"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":"2025-09-14T02:00:10.474Z","response_time":75,"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":[],"created_at":"2025-06-18T03:10:04.088Z","updated_at":"2025-09-14T18:46:40.106Z","avatar_url":"https://github.com/UKPLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PCRF-Seq2Seq\n\nAn adaptation of the MarMot higher-order CRF tagger for generic sequence-to-sequence tasks from [our paper](http://aclweb.org/anthology/C16-1160).\n\n\nPlease use the following citation:\n\n```\n@inproceedings{Schnober:2016:Coling,\n\tauthor = {Carsten Schnober and Steffen Eger and Erik-Lân Do Dinh and Iryna Gurevych},\n\ttitle = {Still not there? Comparing Traditional Sequence-to-Sequence Models to\nEncoder-Decoder Neural Networks on Monotone String Translation Tasks},\n\tmonth = dec,\n\tyear = {2016},\n\tbooktitle = {Proceedings of the 26th International Conference on Computational\nLinguistics (COLING)},\n\tpages = {(1703--1714)},\n\tlocation = {Osaka, Japan},\n\tlanguage = {English},\n}\n```\n\n\u003e **Abstract:** We analyze the performance of encoder-decoder neural models and compare them with well-known established methods. The latter represent different classes of traditional approaches that are applied to the monotone sequence-to-sequence tasks OCR post-correction, spelling correction, grapheme-to-phoneme conversion, and lemmatization.\nSuch tasks are of practical relevance for various higher-level research fields including \\textit{digital humanities}, automatic text correction, and speech recognition. \nWe investigate how well generic deep-learning approaches adapt to these tasks, and how they perform in comparison with established and more specialized methods, including our own adaptation of pruned CRFs. \n\n\nContact persons: \n  * Carsten Schnober, schnober@ukp.informatik.tu-darmstadt.de\n  * Steffen Eger, eger@aiphes.tu-darmstadt.de\n  * Erik-Lân Do Dinh, dodinh@ukp.informatik.tu-darmstadt.de\n\nhttp://www.ukp.tu-darmstadt.de/\n\nhttp://www.tu-darmstadt.de/\n\n\nDon't hesitate to send us an e-mail or report an issue, if something is broken (and it shouldn't be) or if you have further questions.\n\n\u003e This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication. \n\n## Project structure\n\n* `src` -- this folder contains the code and detailed instructions\n* `src/data/` -- sample data from the Twitter typo corpus\n\n## Requirements\nSee [src/README.md](src/README.md) for details!\n\n* [Marmot](https://github.com/muelletm/cistern/) morphological tagger\n* [m2m-aligner](https://github.com/letter-to-phoneme/m2m-aligner) \n\n## Installation and Running\nSee [src/README.md](src/README.md) for details!\n \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukplab%2Fcoling2016-pcrf-seq2seq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fukplab%2Fcoling2016-pcrf-seq2seq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukplab%2Fcoling2016-pcrf-seq2seq/lists"}