Detection of Multiword Expressions for Hindi Language using Word Embeddings and WordNet-based Features.
Dhirendra Singh, Sudha Bhingardive, Kevin Patel, Pushpak Bhattacharyya · 2015
Detection of Multiword Expressions (MWEs) is a challenging problem faced by several natural language processing applications. The dif-ficulty emanates from the task of detecting MWEs with respect to a given context. In this paper, we pro-pose approaches that use Word Em-beddings and WordNet-based fea-tures for the detection of MWEs for Hindi language. These ap-proaches are restricted to two types of MWEs viz., noun compounds and noun+verb compounds. The re-sults obtained indicate that using linguistic information from a rich lexical resource such as WordNet, help in improving the accuracy of MWEs detection. It also demon-strates that the linguistic informa-tion which word embeddings cap-ture from a corpus can be compa-rable to that provided by Word-Net. Thus, we can say that, for the detection of above mentioned MWEs, word embeddings can be a reasonable alternative to WordNet, especially for those languages whose WordNets does not have a better coverage. 1