Dr. Dipti Misra Sharma and her student Riya Pal presented a paper on A Dataset for Semantic Role Labelling for Hindi-English Code-Mixed Tweets at the 13th Linguistic Annotation Workshop co-located with the 57th Annual Meeting of the Association of Computational Linguistics (LAW XIII at ACL 2019) in Florence, Italy from 28 July – 2 August.

Dr. Dipti Misra Sharma and Riya Pal  presented a data set of 1460 Hindi-English code-mixed tweets consisting of 20,949 tokens labelled with Proposition Bank labels marking their semantic roles. They created verb frames for complex predicates present in the corpus and formulated mappings from Paninian dependency labels to Proposition Bank labels. With the help of these mappings and the dependency tree, they propose a baseline rule based system for Semantic Role Labelling of Hindi-English code-mixed data. They obtained an accuracy of 96.74% for Argument Identification and were able to further classify 73.93% of the labels correctly. While there is relevant ongoing research on Semantic Role Labelling (SRL) and on building tools for code-mixed social media data, this is the first attempt at labelling semantic roles in Hindi-English codemixed data, to the best of  their knowledge.

Link to paper: https://www.aclweb.org/anthology/W19-4020