Universal Dependencies Parsing for Colloquial Singaporean English
This work addresses parsing for a low-resource creole language, benefiting computational linguistics and regional social media analysis, though it is incremental in applying neural stacking to cross-lingual parsing.
The paper tackled dependency parsing for Colloquial Singaporean English (Singlish) by constructing a Universal Dependencies treebank and integrating English syntactic knowledge into a neural parser, resulting in a 25% relative error reduction and 84.47% parsing accuracy.
Singlish can be interesting to the ACL community both linguistically as a major creole based on English, and computationally for information extraction and sentiment analysis of regional social media. We investigate dependency parsing of Singlish by constructing a dependency treebank under the Universal Dependencies scheme, and then training a neural network model by integrating English syntactic knowledge into a state-of-the-art parser trained on the Singlish treebank. Results show that English knowledge can lead to 25% relative error reduction, resulting in a parser of 84.47% accuracies. To the best of our knowledge, we are the first to use neural stacking to improve cross-lingual dependency parsing on low-resource languages. We make both our annotation and parser available for further research.