電腦輔助語言學習(Computer-Assisted Language Learning, CALL)是個相當熱門的主題,應用電腦在字彙學習也已有相當多的研究,其中同義詞(Near-synonym)更是第二外語學習中相當困難的部分,同義詞即為意思非常相近,但是用法卻不盡相同的字詞,若非母語學習者,學習第二外語的同義詞是非常不容易的,為了降低學習的困難性,本論文希望藉由電腦來輔助第二外語學習者,在同義詞的學習上,更有效率。 本論文設計了一個同義詞學習系統,搭配七個同義詞集合以及兩種使用文脈資訊的方法:點式交互資訊(Pointwise Mutual Information, PMI)與N連詞(N-gram)模型,輔助學習者學習同義詞間的差異,以及遇到不同上下文時,同義詞的選用。為了測試系統對學習者是否有幫助,本研究收集30位受測者,經過前測與後測的實驗後,結果顯示系統對於導正學習者的錯誤認知上,是明顯有效的。
Computer-assisted language learning (CALL) is an emerging research topic in recent years. Previous studies have investigated the use of computers for vocabulary learning. Near-synonym sets represent groups of words with similar meaning. Although the words in a near-synonym set have similar meaning, they may have different usages in different contexts. Such subtle difference is a major barrier for second language learner in learning near-synonyms. To this end, this paper builds a computer-assisted near-synonym learning system that can provide contextual information for near-synonyms. The contextual information includes pointwise mutual information (PMI) and n-grams. The experimental results show that the propose system can assist students to learn different usages of near-synonyms.