IIT (BHU) submission for the CoNLL-2016 shared task: Shallow Discourse Parsing using Semantic Lexicon

Abstract

This paper describes the Shallow Discourse Parser (SDP) submitted as a part of the Shared Task of CoNLL, 2016. The discourse parser takes newswire text as input and outputs relations between various components of the text. Our system is a pipeline of various sub-tasks which have been elaborated in the paper. We choose a data driven approach for each task and put a special focus on utilizing the resources allowed by the organizers for creating novel features. We also give details of various experiments with the dataset and the lexicon provided for the task. © 2016 Association for Computational Linguistics.