A Method for Extracting Formulaic Sequences from a Student Corpus
Year: 2011
Type: article
Abstract: Use of appropriate formulaic sequences can add fluency, accuracy\nand appropriacy to written English, and one important place these\nsequences occur are as sentence starters such as “Needless to say”\nor “At the same time”. This article describes and provides open\nsource code for a tool created using Python and the Natural Language\nToolkit which can help identify formulaic sentence-starters\nin an untagged corpus of student writing, for use in progress measurement\nand course design. Example results from two corpora are\npresented and discussed.
Source: 神奈川大学言語研究
Author: Malcolm Prentice
Language: Japanese
Subfield: Developmental and Educational Psychology
Field: Psychology
Domain: Social Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W367350508
