Paper: Word Level Language Identification in Online Multilingual Communication

ACL ID D13-1084
Title Word Level Language Identification in Online Multilingual Communication
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

Multilingual speakers switch between lan- guages in online and spoken communication. Analyses of large scale multilingual data re- quire automatic language identification at the word level. For our experiments with mul- tilingual online discussions, we first tag the language of individual words using language models and dictionaries. Secondly, we incor- porate context to improve the performance. We achieve an accuracy of 98%. Besides word level accuracy, we use two new metrics to evaluate this task.