Word Segmentation and Morphological Parsing for Sanskrit
This work addresses a domain-specific problem for Sanskrit language processing, with incremental improvements in existing methods.
The paper tackled word segmentation and morphological parsing for Sanskrit by proposing an end-to-end trainable pipeline model for joint tasks, achieving an 80.018 F1 score in the joint subtask and 96.189 and 69.180 F1 scores in individual segmentation and analysis subtasks, respectively.
We describe our participation in the Word Segmentation and Morphological Parsing (WSMP) for Sanskrit hackathon. We approach the word segmentation task as a sequence labelling task by predicting edit operations from which segmentations are derived. We approach the morphological analysis task by predicting morphological tags and rules that transform inflected words into their corresponding stems. Also, we propose an end-to-end trainable pipeline model for joint segmentation and morphological analysis. Our model performed best in the joint segmentation and analysis subtask (80.018 F1 score) and performed second best in the individual subtasks (segmentation: 96.189 F1 score / analysis: 69.180 F1 score). Finally, we analyse errors made by our models and suggest future work and possible improvements regarding data and evaluation.