Project notes on building a conversation parser on top of a text parser

Abstract

This ongoing doctoral study examines cause and effect relationships in Chinese spoken language corpora and aims to build a tagger (Cause-Chi) that automatically annotates linguistic patterns used to express these relationships. Drawing on insights from Construction Grammar (CxG), Cause-Chi is a tool to detect explicit causal language and automatically parse constructions of causation and their slot-fillers for Chinese conversational corpus data. Built on top of an existing tagger for text corpora, Cause-Chi is designed to not only detect lexical constructions but also conversation-specific causal language such as multi-segment causal expressions and the usage of temporal constructions to express causal relation. Cause-Chi is currently under development and will be released in 2018 together with MYCanCor, a small corpus of spoken Chinese, and a mini-constructicon of causal constructions based on the corpus.