A multilingual person writing a sentence or a piece of text tends to switch between languages s/he is proficient in. This alteration between languages, commonly known as code-switching, presents us with the problem of determining the correct language of each word in the text. My method uses a variety of techniques based upon the observed differences in the formation of words in these languages. My system was able to obtain third position in both tweet and token level for the main test dataset as well as first position in the token level evaluation for the surprise dataset both consisting of Nepali-English codeswitched texts.

A description of a system for identifying Verbal Multi-Word Expressions (VMWEs) in running text is presented. The system mainly exploits universal syntactic dependency features through a Conditional Random Fields (CRF) sequence model. The system competed in the Closed Track at the PARSEME VMWE Shared Task 2017, ranking 2nd place in most languages on full VMWE-based evaluation and 1st in three languages on token-based evaluation. In addition, this paper presents an option to re-rank the 10 best CRF-predicted sequences via semantic vectors, boosting its scores above other systems in the competition. We also show that all systems in the competition would struggle to beat a simple lookup base-line system and argue for a more purpose-specific evaluation scheme.