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

學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Exploring lexical, syntactic, and semantic features for Chinese textual entailment in NTCIR RITE evaluation tasks
作者 Huang, Wei-Jie;Liu, Chao-Lin
黃瑋杰;劉昭麟
貢獻者 資訊科學系
關鍵詞 Textual entailment recognition;Negation and antonyms;Near synonym recognition;Named-entity recognition;Dependency parsing;Trained heuristic functions;Support-vector machines;Linearly weighted models;Decision trees
日期 2017-01
上傳時間 5-Aug-2015 14:29:05 (UTC+8)
摘要 We computed linguistic information at the lexical, syntactic, and semantic levels for Recognizing Inference in Text (RITE) tasks for both traditional and simplified Chinese in NTCIR-9 and NTCIR-10. Techniques for syntactic parsing, named-entity recognition, and near synonym recognition were employed, and features like counts of common words, statement lengths, negation words, and antonyms were considered to judge the entailment relationships of two statements, while we explored both heuristics-based functions and machine-learning approaches. The reported systems showed their robustness by simultaneously achieving second positions in the binary-classification subtasks for both simplified and traditional Chinese in NTCIR-10 RITE-2. We conducted more experiments with the test data of NTCIR-9 RITE, with good results. We also extended our work to search for better configurations of our classifiers and investigated contributions of individual features. This extended work showed interesting results and should encourage further discussions.
關聯 Soft Computing, Volume 21, Issue 2, pp 311–330
資料類型 article
DOI http://dx.doi.org/10.1007/s00500-015-1629-1
dc.contributor 資訊科學系-
dc.creator (作者) Huang, Wei-Jie;Liu, Chao-Lin-
dc.creator (作者) 黃瑋杰;劉昭麟zh_TW
dc.date (日期) 2017-01-
dc.date.accessioned 5-Aug-2015 14:29:05 (UTC+8)-
dc.date.available 5-Aug-2015 14:29:05 (UTC+8)-
dc.date.issued (上傳時間) 5-Aug-2015 14:29:05 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/77420-
dc.description.abstract (摘要) We computed linguistic information at the lexical, syntactic, and semantic levels for Recognizing Inference in Text (RITE) tasks for both traditional and simplified Chinese in NTCIR-9 and NTCIR-10. Techniques for syntactic parsing, named-entity recognition, and near synonym recognition were employed, and features like counts of common words, statement lengths, negation words, and antonyms were considered to judge the entailment relationships of two statements, while we explored both heuristics-based functions and machine-learning approaches. The reported systems showed their robustness by simultaneously achieving second positions in the binary-classification subtasks for both simplified and traditional Chinese in NTCIR-10 RITE-2. We conducted more experiments with the test data of NTCIR-9 RITE, with good results. We also extended our work to search for better configurations of our classifiers and investigated contributions of individual features. This extended work showed interesting results and should encourage further discussions.-
dc.format.extent 7740148 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Soft Computing, Volume 21, Issue 2, pp 311–330-
dc.subject (關鍵詞) Textual entailment recognition;Negation and antonyms;Near synonym recognition;Named-entity recognition;Dependency parsing;Trained heuristic functions;Support-vector machines;Linearly weighted models;Decision trees-
dc.title (題名) Exploring lexical, syntactic, and semantic features for Chinese textual entailment in NTCIR RITE evaluation tasks-
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1007/s00500-015-1629-1-
dc.doi.uri (DOI) http://dx.doi.org/10.1007/s00500-015-1629-1-