Joint Word Segmentation and Stemming with Neural Sequence Labeling for Myanmar Language
Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering · 2019
Word segmentation is widely-studies sequence labeling problem using mach ine learning method like conditional rando m fields.In word segmentation, deep learn ing approaches have achieved state -of-theart performance.Normally, seg mentation is considered as a separate process fro m stemming.Our approach proposes a joint model that has stronger capabilities for Myan mar word segmentation and stemming.As far as we know, this is the first work on joint Myanmar word segmentation and stemming.In this paper, we evaluate the performance o f neural network arch itecture that relies on t wo sources of information about syllable-and character-level representation, by using LSTM, CNN, GRU and CRF.For the co mparison and analysis process, we examine the importance of different network designs and different factors such as the last layer of the network and different optimizers.