Morfessor-enriched features and multilingual training for canonical morphological segmentation

Abstract

In our submission to the SIGMORPHON 2022 Shared Task on Morpheme Segmentation, we study whether an unsupervised morphological segmentation method, Morfessor, can help in a supervised setting. Previous research has shown the effectiveness of the approach in semi-supervised settings with small amounts of labeled data. The current tasks vary in data size: the amount of word-level annotated training data is much larger, but the amount of sentence-level annotated training data remains small. Our approach is to pre-segment the input data for a neural sequence-to-sequence model with the unsupervised method. As the unsupervised method can be trained with raw text data, we use Wikipedia to increase the amount of training data. In addition, we train multilingual models for the sentence-level task. The results for the Morfessor-enriched features are mixed, showing benefit for all three sentence-level tasks but only some of the word-level tasks. The multilingual training yields considerable improvements over the monolingual sentence-level models, but it negates the effect of the enriched features.