| Summary: | 碩士 === 國立清華大學 === 資訊系統與應用研究所 === 93 === Collocation has been acknowledged as a crucial aspect in vocabulary learning but the area has long been neglected in foreign language teaching. Previous work in the literature reveals that EFL learners were seriously deficient in collocations which are a hallmark of near native fluency in learner’s writing; good learner-writers used collocation more appropriately and frequently than poor learner-writers did. Among different types of collocation, the verb-noun (V-N) type was found to be particularly difficult for Taiwanese learners to master. Studies on EFL learners’ miscollocations also indicated that learners’ first language would heavily influence their production of collocations. We develop an online collocation aid for EFL writers in Taiwan, aiming at detection and correction of learners’ miscollocations attributable to L1 interference. Relevant correct collocation as feedback messages is suggested according to the mutual translations between learner’s L1 and L2. The system utilizes natural language processing (NLP) techniques to chunk sentences in order to extract V-N collocations in input texts, and to derive a list of candidate English verbs that share the same Chinese translations via processing of bilingual corpora. After combining nouns with those candidate verbs as V-N pairs, the system makes use of a reference English corpus to exclude the inappropriate V-N pairs so as to single out the proper collocations. The system can pinpoint the miscollocation and prompt the learner with suggestions of correct collocations that the learner intends to write but misuses. It is hoped that this online assistant can facilitate EFL learner-writers’ collocation use and transfer that knowledge to their future writing.
|
|---|
