Paper: Automatic Collocation Suggestion in Academic Writing

ACL ID P10-2021
Title Automatic Collocation Suggestion in Academic Writing
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2010

In recent years, colocation has ben widely acknowledged as an esential characteristic to distinguish native speak- ers from non-native speakers. Research on academic writing has also shown that colocations are not only comon but serve a particularly important discourse function within the academic comunity. In our study, we propose a machine learning aproach to implementing an online collocation writing asistant. We use a data-driven clasifier to provide colocation sugestions to improve word choices, based on the result of classifica- tion. The system generates and ranks sugestions to assist learners’ colocation usages in their academic writing with sat- isfactory results. *