{"id":19168381,"url":"https://github.com/bloomberg/emnlp20_depsrl","last_synced_at":"2025-05-07T14:41:11.243Z","repository":{"id":66125169,"uuid":"320403529","full_name":"bloomberg/emnlp20_depsrl","owner":"bloomberg","description":"Research code and scripts used in the paper Semantic Role Labeling as Syntactic Dependency Parsing.","archived":false,"fork":false,"pushed_at":"2023-06-12T21:29:54.000Z","size":39,"stargazers_count":14,"open_issues_count":1,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-19T23:31:57.837Z","etag":null,"topics":["dependency-parsing","emnlp","emnlp2020","nlp","semantic-role-labeling"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"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/bloomberg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSES/Apache_2.0_License","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-12-10T22:18:53.000Z","updated_at":"2025-04-07T07:50:49.000Z","dependencies_parsed_at":"2023-06-26T00:04:22.431Z","dependency_job_id":null,"html_url":"https://github.com/bloomberg/emnlp20_depsrl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloomberg%2Femnlp20_depsrl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloomberg%2Femnlp20_depsrl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloomberg%2Femnlp20_depsrl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bloomberg%2Femnlp20_depsrl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bloomberg","download_url":"https://codeload.github.com/bloomberg/emnlp20_depsrl/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252897330,"owners_count":21821425,"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","emnlp","emnlp2020","nlp","semantic-role-labeling"],"created_at":"2024-11-09T09:42:28.979Z","updated_at":"2025-05-07T14:41:11.217Z","avatar_url":"https://github.com/bloomberg.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# srl-dep\n\n**Author:** Tianze Shi\n\n## About this repo\n\nThis repo contains the research code and scripts used in the paper [Semantic Role Labeling as Syntactic Dependency Parsing](https://arxiv.org/abs/2010.11170). This README file aims at giving basic overviews of the code structure and its major components. For more questions, please directly contact the authors.\n\n## Code structure\n\nThe entrance point to the package is [here](srl/parser.py). Calls to this package can be chained through fire CLI. The order of calling should usually be `build-vocab`, `create-parser`, `load-embeddings`, `train` and then finally `finish`.\nAn example inference script is [here](test.py) using `parser.evaluate(data)` after loading in models and embeddings.\n\nFor official CoNLL evaluation script, access at [https://www.cs.upc.edu/~srlconll/soft.html](https://www.cs.upc.edu/~srlconll/soft.html). The F1 scores displayed during model training are NOT official F1 scores (though they are usually very close).\n\n### SRL parsing module\n\nThe major parsing module is within the python class `SRLDepParser` inside [this file](srl/modules.py). Back-and-forth conversion algorithms tuned on OntoNotes 5.0 data are contained in [this file](srl/conversion.py).\n\n### Pre-trained word embeddings\n\nTo speed up loading time, we can process the embedding files to trim down to only the vocabulary seen in our data. Script for trimming is [here](srl/filter_embeddings.py).\n\n### Data preparation\n\nData preparation scripts lie under `data_prep` folder.\n\nPrerequisite: [Stanford CoreNLP with English and Chinese models v3.9.2](https://stanfordnlp.github.io/CoreNLP/history.html)\n\n1. Follow http://cemantix.org/data/ontonotes.html to prepare data, using v12 data release\n2. For Chinese data (http://conll.cemantix.org/2012/data.html), copy folders under the correct splits\n3. Use train dev and conll-2012-test splits for English, train dev, test for Chinese\n4. Run `aggregate.sh`\n5. Run `space_to_tab.sh`\n6. Run `constituency_tree.sh`\n7. Run `english_dep_tree.sh` and `english_fuse.py` for English data preparation\n8. Run `chinese_dep_tree.sh` and `chinese_fuse.py` for Chinese data preparation\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbloomberg%2Femnlp20_depsrl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbloomberg%2Femnlp20_depsrl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbloomberg%2Femnlp20_depsrl/lists"}