1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Proceedings
  5. Item

學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 Attachment of english prepositional phrases and suggestions of english prepositions
作者 Tsai, Chia-Chi;Liu, Chaolin
劉昭麟
貢獻者 資科系
關鍵詞 Classification models; Computational procedures; Machine translations; Prepositional phrase; Semantic analysis; Semantic features; Semantic information; Text proofreading; Abstracting; Computational linguistics; Semantics; Speech processing; Problem solving
日期 2012
上傳時間 10-Apr-2015 15:35:07 (UTC+8)
摘要 This paper focuses on problems of attachment of prepositional phrases (PPs) and problems of prepositional suggestions. We transform the problems of PPs attachment and prepositional suggestions into an abstract model, and apply the same computational procedures to solve these two problems. The common model features four headwords, i.e., the verb, the first noun, the preposition, and the second noun in the prepositional phrases. Our methods consider the semantic features of the headwords in WordNet to train classification models, and apply the learned models for tackling the attachment and suggestion problems. This exploration of PP attachment problems is special in that only those PPs that are almost equally possible to attach to the verb and the first noun were used in the study. The proposed models consider only four headwords to achieve satisfactory performances. This study reconfirms that semantic information is instrument for both PP attachment and prepositional suggestions.
關聯 Proceedings of the 24th Conference on Computational Linguistics and Speech Processing, ROCLING 2012，32-46
資料類型 conference
dc.contributor 資科系
dc.creator (作者) Tsai, Chia-Chi;Liu, Chaolin
dc.creator (作者) 劉昭麟zh_TW
dc.date (日期) 2012
dc.date.accessioned 10-Apr-2015 15:35:07 (UTC+8)-
dc.date.available 10-Apr-2015 15:35:07 (UTC+8)-
dc.date.issued (上傳時間) 10-Apr-2015 15:35:07 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/74457-
dc.description.abstract (摘要) This paper focuses on problems of attachment of prepositional phrases (PPs) and problems of prepositional suggestions. We transform the problems of PPs attachment and prepositional suggestions into an abstract model, and apply the same computational procedures to solve these two problems. The common model features four headwords, i.e., the verb, the first noun, the preposition, and the second noun in the prepositional phrases. Our methods consider the semantic features of the headwords in WordNet to train classification models, and apply the learned models for tackling the attachment and suggestion problems. This exploration of PP attachment problems is special in that only those PPs that are almost equally possible to attach to the verb and the first noun were used in the study. The proposed models consider only four headwords to achieve satisfactory performances. This study reconfirms that semantic information is instrument for both PP attachment and prepositional suggestions.
dc.format.extent 176 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) Proceedings of the 24th Conference on Computational Linguistics and Speech Processing, ROCLING 2012，32-46
dc.subject (關鍵詞) Classification models; Computational procedures; Machine translations; Prepositional phrase; Semantic analysis; Semantic features; Semantic information; Text proofreading; Abstracting; Computational linguistics; Semantics; Speech processing; Problem solving
dc.title (題名) Attachment of english prepositional phrases and suggestions of english prepositions
dc.type (資料類型) conferenceen