Transfer learning for dependency parsing of Vedic Sanskrit

AbstractThis paper focuses on data-driven dependency parsing for Vedic Sanskrit. We propose and evaluate a transfer learning approach that benefits from syntactic analysis of typologically related languages, including Ancient Greek and Latin, and a descendant language - Classical Sanskrit. Experiments on the Vedic TreeBank demonstrate the effectiveness of cross-lingual transfer, demonstrating improvements from the biaffine baseline as well as outperforming the current state of the art benchmark, the deep contextualised self-training algorithm, across a wide range of experimental setups.