{"id":38553860,"url":"https://github.com/compnet/splice","last_synced_at":"2026-01-17T07:39:03.428Z","repository":{"id":268540664,"uuid":"815436472","full_name":"CompNet/Splice","owner":"CompNet","description":"The Role of Information Extraction Tasks in Automatic Literary Character Network Construction","archived":false,"fork":false,"pushed_at":"2024-12-17T11:10:55.000Z","size":154,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-10T05:06:25.029Z","etag":null,"topics":["alias-resolution","character-networks","literary-texts","ner","nlp"],"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/CompNet.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-15T06:47:09.000Z","updated_at":"2025-01-30T09:03:44.000Z","dependencies_parsed_at":"2024-12-17T12:33:33.324Z","dependency_job_id":null,"html_url":"https://github.com/CompNet/Splice","commit_stats":null,"previous_names":["compnet/splice"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CompNet/Splice","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CompNet%2FSplice","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CompNet%2FSplice/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CompNet%2FSplice/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CompNet%2FSplice/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CompNet","download_url":"https://codeload.github.com/CompNet/Splice/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CompNet%2FSplice/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28504356,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T06:57:29.758Z","status":"ssl_error","status_checked_at":"2026-01-17T06:56:03.931Z","response_time":85,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["alias-resolution","character-networks","literary-texts","ner","nlp"],"created_at":"2026-01-17T07:39:03.341Z","updated_at":"2026-01-17T07:39:03.412Z","avatar_url":"https://github.com/CompNet.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Splice\n*The Role of Information Extraction Tasks in Automatic Literary Character Network Construction*\n\n## Reproducing Results\n\nFirst, you should:\n\n- install dependencies. Either use `poetry install` if you have poetry, or `pip install -r requirements.txt` otherwise.\n- get the [litbank dataset](https://github.com/dbamman/litbank)\n\nThe main experiment can be run with `xp.py`:\n\n```sh\npython xp.py with\\\n\t   min_graph_nodes=10\\\n\t   co_occurrences_dist=32\\\n\t   litbank.root=\"/path/to/litbank\"\n```\n\n\n### Degradation Experiments\n\nThe following script will run all of the degradation experiments:\n\n```sh\nMAIN_XP_RUN=\"/path/to/main/xp/run\"\n\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=NER degradation_name=add_wrong_entity degradation_steps=1000 degradation_report_frequency=0.05\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=NER degradation_name=remove_correct_entity degradation_steps=200 degradation_report_frequency=0.5\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=coref degradation_name=add_wrong_mention degradation_steps=200 degradation_report_frequency=0.05\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=coref degradation_name=remove_correct_mention degradation_steps=1000 degradation_report_frequency=0.05\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=coref degradation_name=add_wrong_link degradation_steps=500 degradation_report_frequency=0.05\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=coref degradation_name=remove_correct_link degradation_steps=1000 degradation_report_frequency=0.05\npython xp_metrics_over_degradation.py with input_dir=\"${MAIN_XP_RUN}\" task_name=coref degradation_name=coref_all degradation_steps=1000 degradation_report_frequency=0.05\n```\n\n\n### End-to-end LLM-based Pipelines\n\nThe *E2E-Coref* experiment can be reproduced with the `xp_e2e_llm_coref.py` script:\n\n```sh\nMAIN_XP_RUN=\"/path/to/main/xp/run\"\nLITBANK_PATH=\"/path/to/litbank\"\n\npython xp_e2e_llm_coref.py with\\\n\t   input_dir=\"${MAIN_XP_RUN}\"\\\n\t   model=\"gpt3.5\"\\\n\t   openAI_API_key=\"insert your openAI key\"\\\n\t   litbank.root=\"${LITBANK_PATH}\"\n\npython xp_e2e_llm_coref.py with\\\n\t   input_dir=\"${MAIN_XP_RUN}\"\\\n\t   model=\"gpt40\"\\\n\t   openAI_API_key=\"insert your openAI key\"\\\n\t   litbank.root=\"${LITBANK_PATH}\"\n\npython xp_e2e_llm_coref.py with\\\n\t   input_dir=\"${MAIN_XP_RUN}\"\\\n\t   model=\"llama3-8b-instruct\"\\\n\t   hg_access_token=\"insert your Huggingface access token\"\\\n\t   device=\"cuda\"\\\n\t   litbank.root=\"${LITBANK_PATH}\"\n```\n\nSimilarly, the *E2E-Graphml experiment can be reproduced with the `xp_e2e_llm_graphml.py` script:\n\n```sh\nMAIN_XP_RUN=\"/path/to/main/xp/run\"\n\npython xp_e2e_llm_graphml.py with\\\n\t   input_dir=\"${MAIN_XP_RUN}\"\\\n\t   model=\"gpt3.5\"\\\n\t   openAI_API_key=\"insert your openAI key\"\\\n\t   litbank.root=\"${LITBANK_PATH}\"\n\npython xp_e2e_llm_graphml.py with\\\n\t   input_dir=\"${MAIN_XP_RUN}\"\\\n\t   model=\"gpt40\"\\\n\t   openAI_API_key=\"insert your openAI key\"\\\n\t   litbank.root=\"${LITBANK_PATH}\"\n\npython xp_e2e_llm_graphml.py with\\\n\t   input_dir=\"${MAIN_XP_RUN}\"\\\n\t   model=\"llama3-8b-instruct\"\\\n\t   hg_access_token=\"insert your Huggingface access token\"\\\n\t   device=\"cuda\"\\\n\t   litbank.root=\"${LITBANK_PATH}\"\n```\n\n\n### Printing / Plotting Results\n\n| Figure   | Corresponding Script                |\n|----------|-------------------------------------|\n| Table 1  | `print_main_task_results.py`        |\n| Table 2  | `print_main_graph_results.py`       |\n| Table 3  |                                     |\n| Figure 1 | `plot_degradation_metrics.py`       |\n| Figure 2 | `plot_ner_degradation_metrics.py`   |\n| Figure 3 | `plot_coref_degradation_metrics.py` |\n| Table 4  | `print_e2e_graph_results.py`        |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcompnet%2Fsplice","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcompnet%2Fsplice","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcompnet%2Fsplice/lists"}