Universal Dependencies Parsing for Colloquial Singaporean English

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1732–1744 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1159 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1732–1744 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1159 Universal Dependencies Parsing for Colloquial Singaporean English Hongmin Wang†, Yue Zhang†, GuangYong Leonard Chan‡, Jie Yang†, Hai Leong Chieu‡ † Singapore University of Technology and Design {hongmin wang, yue zhang}@sutd.edu.sg jie yang@mymail.sutd.edu.sg ‡ DSO National Laboratories, Singapore {cguangyo, chaileon}@dso.org.sg Abstract Singlish can be interesting to the ACL community both linguistically as a ma- jor creole based on English, and compu- tationally for information extraction and sentiment analysis of regional social me- dia. We investigate dependency pars- ing of Singlish by constructing a depen- dency treebank under the Universal De- pendencies scheme, and then training a neural network model by integrating En- glish syntactic knowledge into a state-of- the-art parser trained on the Singlish tree- bank. Results show that English knowl- edge can lead to 25% relative error reduc- tion, resulting in a parser of 84.47% ac- curacies. 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 fur- ther research. 1 Introduction Languages evolve temporally and geographically, both in vocabulary as well as in syntactic struc- tures. When major languages such as English or French are adopted in another culture as the pri- mary language, they often mix with existing lan- guages or dialects in that culture and evolve into a stable language called a creole. Examples of cre- oles include the French-based Haitian Creole, and Colloquial Singaporean English (Singlish) (Mian- Lian and Platt, 1993), an English-based creole. While the majority of the natural language pro- cessing (NLP) research attention has been focused on the major languages, little work has been done on adapting the components to creoles. One no- table body of work originated from the featured translation task of the EMNLP 2011 Workshop on Statistical Machine Translation (WMT11) to translate Haitian Creole SMS messages sent dur- ing the 2010 Haitian earthquake. This work high- lights the importance of NLP tools on creoles in crisis situations for emergency relief (Hu et al., 2011; Hewavitharana et al., 2011). Singlish is one of the major languages in Sin- gapore, with borrowed vocabulary and grammars1 from a number of languages including Malay, Tamil, and Chinese dialects such as Hokkien, Can- tonese and Teochew (Leimgruber, 2009, 2011), and it has been increasingly used in written forms on web media. Fluent English speakers unfamiliar with Singlish would find the creole hard to com- prehend (Harada, 2009). Correspondingly, fun- damental English NLP components such as POS taggers and dependency parsers perform poorly on such Singlish texts as shown in Table 2 and 4. For example, Seah et al. (2015) adapted the Socher et al. (2013) sentiment analysis engine …

Content truncated to 500 words