電腦輔助克漏詞多選題出題系統之研究

• Main Authors: 王俊弘, Wang , Chun-Hung
• Language: 中文
• Published: 國立政治大學
• Subjects: 電腦輔助語言學習; 自動產生試題; 試題編寫工具; 詞義辨析; 自然語言處理; Computer-Assisted Language Learning; Automatic Item Generation; Authoring Tools; Word Sense Disambiguation; Natural Language Processing
• Online Access: http://thesis.lib.nccu.edu.tw/cgi-bin/cdrfb3/gsweb.cgi?o=dstdcdr&i=sid=%22G0091753024%22.

多選題測驗試題已證明能有效地評估學生的學習成效，然而，以人為方式建立題庫是一件耗時費力的工作。藉由電腦高速運算的能力，電腦輔助產生試題系統能有效率地建置大規模的題庫，同時減少人為的干預而得以保持試題的隱密性。受惠於網路上充裕的文字資源，本研究發展一套克漏詞試題出題系統，利用既有的語料自動產生涵蓋各種不同主題的克漏詞試題。藉由分析歷屆大學入學考試的資料，系統可產生類似難度的模擬試題，並且得到出題人員在遴選測驗標的方面的規律性。在產生試題的過程中導入詞義辨析的演算法，利用詞典與selectional preference模型的輔助，分析句子中特定詞彙的語義，以擷取包含測驗編撰者所要測驗的詞義的句子，並以collocation為基礎的方法篩選誘答選項。實驗結果顯示系統可在每產生1.6道試題中，得到1道可用的試題。我們嘗試產生不同類型的試題，並將這套系統融入網路線上英文測驗的環境中，依學生的作答情形分析試題的鑑別度。 === Multiple-choice tests have proved to be an efficient tool for measuring students’ achievement. Manually constructing tests items, however, is a time- consuming and labor-intensive task. Harnessing the computing power of computers, computer-assisted item generation offers the possibility of creating large amount of items, thereby alleviating the problem of keeping the items secure. With the abundant text resource on the Web, this study develops a system capable of generating cloze items that cover a wide range of topics based on existing corpra. By analyzing training data from the College Entrance Examinations in Taiwan, we identify special regularities of the test items, and our system can generate items of similar style based on results of the analysis. We propose a word sense disambiguation-based method for locating sentences in which designated words carry specific senses, and apply collocation-based methods for selecting distractors. Experimental results indicate that our system was able to produce a usable item for every 1.6 items it returned. We try to create different types of items and integrate the reported item generator in a Web-based system for learning English. The outcome of on-line examinations is analyzed in order to estimate the item discrimination of the test items generated by our system.