{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/glen-general-purpose-event-detection-for","title":"GLEN: General-Purpose Event Detection for Thousands of Types","arxiv_id":"2303.09093","date":"2023-03-16","proceeding":null,"authors":["Qiusi Zhan","Sha Li","Kathryn Conger","Martha Palmer","Heng Ji","Jiawei Han"],"abstract":"The progress of event extraction research has been hindered by the absence of wide-coverage, large-scale datasets. To make event extraction systems more accessible, we build a general-purpose event detection dataset GLEN, which covers 205K event mentions with 3,465 different types, making it more than 20x larger in ontology than today's largest event dataset. GLEN is created by utilizing the DWD Overlay, which provides a mapping between Wikidata Qnodes and PropBank rolesets. This enables us to use the abundant existing annotation for PropBank as distant supervision. In addition, we also propose a new multi-stage event detection model CEDAR specifically designed to handle the large ontology size in GLEN. We show that our model exhibits superior performance compared to a range of baselines including InstructGPT. Finally, we perform error analysis and show that label noise is still the largest challenge for improving performance for this new dataset. Our dataset, code, and models are released at \\url{https://github.com/ZQS1943/GLEN}.}","url_abs":"https://arxiv.org/abs/2303.09093v3","url_pdf":"https://arxiv.org/pdf/2303.09093v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"glen-general-purpose-event-detection-for","repo_url":"https://github.com/zqs1943/glen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"event-extraction","task_name":"Event Extraction"}],"methods":[{"method_slug":"ontology","method_name":"Ontology"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09093"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/ZQS1943/GLEN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":15,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e8a22e3d63e08e3e","entry":"collate_fn_TC_sen","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/dataset.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8a22e3d63e08e3e"}},{"code_sha256_prefix":"8475e39d13821a6d","entry":"collate_fn_TI_sen","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/dataset.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8475e39d13821a6d"}},{"code_sha256_prefix":"9be8a0b5e69c13f1","entry":"collate_fn_TR_sen","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/dataset.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9be8a0b5e69c13f1"}},{"code_sha256_prefix":"e1211212d3a27669","entry":"evaluate","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/predict_type_classifier.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/predict_type_classifier.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1211212d3a27669"}},{"code_sha256_prefix":"38ff6aab7932baab","entry":"flatten_and_batch_shift_indices","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/allennlp_span_utils.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/allennlp_span_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38ff6aab7932baab"}},{"code_sha256_prefix":"4c689d496eb7575b","entry":"get_context_representation_multiple_mentions_idxs","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/data_process.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/data_process.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c689d496eb7575b"}},{"code_sha256_prefix":"577de867e8601b82","entry":"get_device_of","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/allennlp_span_utils.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/allennlp_span_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"577de867e8601b82"}},{"code_sha256_prefix":"ed37d2c4c5923196","entry":"get_model_obj","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/encoder.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/encoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed37d2c4c5923196"}},{"code_sha256_prefix":"a332aeb0adc8f092","entry":"get_optimizer","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/optimizer.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a332aeb0adc8f092"}},{"code_sha256_prefix":"8b5bf32ce9d8e16c","entry":"get_range_vector","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/allennlp_span_utils.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/allennlp_span_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b5bf32ce9d8e16c"}},{"code_sha256_prefix":"c2e8a2dd778aadba","entry":"loss_for_type_classification","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/encoder.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/encoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2e8a2dd778aadba"}},{"code_sha256_prefix":"f767a4a3eb97ee72","entry":"loss_for_type_ranking","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/encoder.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/encoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f767a4a3eb97ee72"}},{"code_sha256_prefix":"37504ee9631718e0","entry":"predict_top_k","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/predict_type_ranking.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/predict_type_ranking.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37504ee9631718e0"}},{"code_sha256_prefix":"9171f21b673fd36e","entry":"sentence_tokenization","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/predict_sentence.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/predict_sentence.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9171f21b673fd36e"}},{"code_sha256_prefix":"528d054aece22a60","entry":"sort_mentions","repo":"ZQS1943/GLEN","repo_kind":"official","path":"model/data_process.py","file_url":"https://github.com/ZQS1943/GLEN/blob/HEAD/model/data_process.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"528d054aece22a60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}