{"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/neural-architectures-for-fine-grained-entity","title":"Neural Architectures for Fine-grained Entity Type Classification","arxiv_id":"1606.01341","date":"2016-06-04","proceeding":"EACL 2017 4","authors":["Sonse Shimaoka","Pontus Stenetorp","Kentaro Inui","Sebastian Riedel"],"abstract":"In this work, we investigate several neural network architectures for\nfine-grained entity type classification. Particularly, we consider extensions\nto a recently proposed attentive neural architecture and make three key\ncontributions. Previous work on attentive neural architectures do not consider\nhand-crafted features, we combine learnt and hand-crafted features and observe\nthat they complement each other. Additionally, through quantitative analysis we\nestablish that the attention mechanism is capable of learning to attend over\nsyntactic heads and the phrase containing the mention, where both are known\nstrong hand-crafted features for our task. We enable parameter sharing through\na hierarchical label encoding method, that in low-dimensional projections show\nclear clusters for each type hierarchy. Lastly, despite using the same\nevaluation dataset, the literature frequently compare models trained using\ndifferent data. We establish that the choice of training data has a drastic\nimpact on performance, with decreases by as much as 9.85% loose micro F1 score\nfor a previously proposed method. Despite this, our best model achieves\nstate-of-the-art results with 75.36% loose micro F1 score on the well-\nestablished FIGER (GOLD) dataset.","url_abs":"http://arxiv.org/abs/1606.01341v2","url_pdf":"http://arxiv.org/pdf/1606.01341v2.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":"neural-architectures-for-fine-grained-entity","repo_url":"https://github.com/shimaokasonse/NFGEC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"type","task_name":"Vocal Bursts Type Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1606.01341","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}