Neural Approaches for Data Driven Dependency Parsing in Sanskrit

TL;DR

This paper evaluates four data-driven dependency parsing models on Sanskrit, analyzing their performance in low-resource settings and the impact of word order, to advance NLP tools for morphologically rich languages.

Contribution

It compares four existing parsing models on Sanskrit without language-specific features, highlighting their effectiveness in low-resource and varied word order scenarios.

Findings

Graph-based and transition-based parsers perform variably on Sanskrit.

Models show robustness in low-resource settings with 1,500 sentences.

Word order significantly impacts parsing accuracy.

Abstract

Data-driven approaches for dependency parsing have been of great interest in Natural Language Processing for the past couple of decades. However, Sanskrit still lacks a robust purely data-driven dependency parser, probably with an exception to Krishna (2019). This can primarily be attributed to the lack of availability of task-specific labelled data and the morphologically rich nature of the language. In this work, we evaluate four different data-driven machine learning models, originally proposed for different languages, and compare their performances on Sanskrit data. We experiment with 2 graph based and 2 transition based parsers. We compare the performance of each of the models in a low-resource setting, with 1,500 sentences for training. Further, since our focus is on the learning power of each of the models, we do not incorporate any Sanskrit specific features explicitly into the models, and rather use the default settings in each of the paper for obtaining the feature functions. In this work, we analyse the performance of the parsers using both an in-domain and an out-of-domain test dataset. We also investigate the impact of word ordering in which the sentences are provided as input to these systems, by parsing verses and their corresponding prose order (anvaya) sentences.