Exploring Semantic Information in Hindi WordNet for Hindi Dependency Parsing

In this paper, we present our efforts towards incorporating external knowledge from Hindi WordNet to aid dependency parsing. We conduct parsing experiments on Hindi, an Indo-Aryan language, utilizing the information from concept ontologies available in Hindi WordNet to complement the morpho-syntactic information already available. The work is driven by the insight that concept ontologies capture a specific real world aspect of lexical items, which is quite distinct and unlikely to be deduced from morpho-syntactic information such as morph, POS-tag and chunk. This complementing information is encoded as an additional feature for data driven parsing and experiments are conducted. We perform experiments over datasets of different sizes. We achieve an improvement of 1.1% (LAS) when training on 1,000 sentences and 0.2% (LAS) on 13,371 sentences over the baseline. The improvements are statistically significant at p<0.01. The higher improvements on 1,000 sentences suggest that the semantic information could address the data sparsity problem.