個人化電腦輔助出題於英文學習之研究

Personalized Computer-aided Question Generation for English Language Learning

黃意婷(Yi-Ting Huang)

指導教授 ： 孫雅麗

國立臺灣大學/管理學院/資訊管理學研究所/博士(2014年)

https://doi.org/10.6342/NTU.2014.03128

摘要

過去幾年來，電腦輔助自動出題(Computer-aided Question Generation)研究在結合自然語言處理(Natural Language Processing) 的技術和計算語言學(Computational Linguistics)的方法，受到電腦輔助語言學習(Computer-assisted Language Learning)領域中越來越多的關注。為了提供以英文為第二外語的學習者自我學習評量，本研究提出個人化方法，以判斷學習教材難易度及評估學生程度的機制，應用於電腦輔助自動出題。在判斷閱讀難易度(Reading Difficulty Esti-mation)部分，根據學生的學習教材，考量豐富的語言特徵以及學生語言習得年級分布(language acquisition grade distributions)，針對第二語言學習特性，提出適合第二語言學習者閱讀難易度分析；在評估學生程度 (Ability Estimation)的部分，結合 (Item Response Theory)和年級分布，考量受試者長期的測驗結果來估計學生實際程度。在自動出題的部分，考量單字、文法與閱讀能力有交互作用影響，提出不同難度的單字、文法與閱讀測驗出題方法，利用評估學生程度機制獲得學生的能力估計，抽取與學生程度相符的閱讀素材和考題進行測驗，考試的結果也作為下一次個人化出題參考。實驗結果顯示閱讀難易度估計和能力程度評估可以比過去相關研究還要準確；此外，透過個人化電腦輔助出題系統的協助下，學習者可以減少重複犯錯，並且有明顯的進步。

關鍵字

電腦輔助自動出題 ； 閱讀難易度評估 ； 學生能力程度估計 ； 項目反應理論 ； 電腦輔助語言學習

並列摘要

In recent years, there has been increasing attention to computer-aided question generation in the field of computer assisted language learning and Natural Language Processing (NLP). However, the previous related work often provides examinees with an exhaustive amount of questions that are not designed for any specific testing pur-pose. In this study, we present a personalized automatic quiz generation that generates multiple–choice questions at various difficulty levels and categories, including grammar, vocabulary, and reading comprehension. We also design a reading difficulty estimation to predict the readability of a reading material, for learners taking English as a foreign language. The proposed reading difficulty estimation is based not only on the complex-ity of lexical and syntactic features, but also on several novel concepts, including the word and grammar acquisition grade distributions from several sources, word sense from WordNet, and the implicit relations between sentences. Moreover, we combine the proposed question generation with a quiz strategy for estimating a student’s ability and question selection. We develop a statistical and interpretable ability estimation. This method captures the succession of learning over time and provides an explainable interpretation of a statistical measurement, based on the quantiles of acquisition distri-butions and Item Response Theory (IRT). The concepts behind incorrectly answered questions are reincorporated into future tests in order to improve the weaknesses of examinees. The results showed that proposed second language reading difficulty esti-mation outperforms other first language reading difficulty estimations and the pro-posed ability estimation showed more accurate and robust than other ability estimations. In an empirical study, the results showed that the subjects with the personalized auto-matic quiz generation corrected their mistakes more frequently than ones only with computer–aided question generation. Moreover, subjects demonstrated the most pro-gress between the pre–test and post–test and correctly answered more difficult ques-tions.

並列關鍵字

Computer-aided question generation ； reading difficulty estimation ； ability estimation ； Item Response Theory ； Computer assisted language learning

參考文獻

[4] Anderson, R. C., & Biddle, W. B. (1975). On asking people questions about what they are reading. Psychology of learning and motivation, 9, 89-132.

[6] Baker, F. B. (1993). Equating tests under the nominal response model. Applied Psychological Measurement, 17, 239-251.

[8] Barla, M., Bielikova, M., Ezzeddinne, A. B., Kramar, T., Simko, M. & Vozar, O. (2010). On the impact of adaptive test question selection for learning efficiency. Computer & Education, 55(2), 846–857.

[9] Barzilay, R. and Lapata, M. (2008). Modeling local coherence: An entity-based approach. Computational Linguistics, 34(1), 1-34.

[10] Brown, R. G. (2004). Smoothing, forecasting and prediction of discrete time series. New York: Dover Publications.