Automatic extraction of fixed multiword expressions

概要

論文の詳細を見る
Fixed multiword expressions are strings of words which together behave like a single word. This research establishes a method for the automatic extraction of such expressions. Our method involves three stages. In the first, statistical measures are used to extract candidate bigrams. In the second, we use this list to select occurrences of candidate expressions in a corpus, together with their surrounding contexts. These examples are used as training data for supervised machine learning, resulting in a classifier which can identify true multiword expressions. The final stage is the estimation of the parts of speech of the extracted expressions. Evaluation demonstrated that collocation measures alone are not effective in identifying target expressions. However, when trained on one million examples, the classifier identified true multiword expressions with precision greater than 90%. Part of speech estimation had precision and recall of over 95% for the part of speech types measured.
一般社団法人情報処理学会の論文
2005-05-26