2024-03-28T23:45:53Zhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_oaipmhoai:ipsj.ixsq.nii.ac.jp:001564192017-03-31T05:33:31Z08512:08642:08643:08588:08590
G_012 Using Ontological Knowledge to Disambiguate Unknown Words in Semantic Taggingenghttp://id.nii.ac.jp/1001/00156385/Conference Paperhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_action_common_download&item_id=156419&item_no=1&attribute_id=1&file_no=1Copyright (c) 2006 by IEICE,IPSJ独立行政法人情報通信研究機構:ATR音声言語コミュニケーション研究所独立行政法人情報通信研究機構:ATR音声言語コミュニケーション研究所フィンチ, アンドリュー隅田, 英一郎This paper presents a detailed study of the integration of knowledge from hierarchical word ontologies into a maximum-entropy-based tagging model that simultaneously labels words with both syntax and semantics. Our findings show that ontological information can lead to strong improvements in overall system accuracy, and in particular increased accuracy for words not seen in the training data.AA11740605情報科学技術フォーラム一般講演論文集523773802006-08-212016-02-18