A Learner Corpus-based Approach to Verb Suggestion for ESL
A Learner Corpus-based Approach to Verb Suggestion for ESL
复制标题
基于学习者语料库的 ESL 动词建议方法
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Yu Sawai;Mamoru Komachi;Yuji Matsumoto
我们提出了一种动词建议方法，该方法使用候选集和领域自适应来整合ESL学习者产生的错误模式。候选集是由一个大规模的学习者语料库构建的，以涵盖学习者产生的各种错误模式。此外，该模型通过领域自适应技术同时使用本地语料库和学习者语料库进行训练。在两个学习语料库上的实验表明，候选集增加了错误模式的覆盖率，领域自适应提高了动词提示的性能。
We propose a verb suggestion method which uses candidate sets and domain adaptation to incorporate error patterns produced by ESL learners. The candidate sets are constructed from a large scale learner corpus to cover various error patterns made by learners. Furthermore, the model is trained using both a native corpus and the learner corpus via a domain adaptation technique. Experiments on two learner corpora show that the candidate sets increase the coverage of error patterns and domain adaptation improves the performance for verb suggestion.