Interpretation of Chinese discourse connectives for explicit discourse relation recognition
Journal
25th International Conference on Computational Linguistics, Proceedings of COLING
Pages
632-643
ISBN
9781941643266
Date Issued
2014
Author(s)
Abstract
This paper addresses the specific features of Chinese discourse connectives, including types (word-pair and single-word), linking directions (forward and backward linking), positions and ambiguous degrees, and discusses how they affect the discourse relation recognition. A semisupervised learning method is proposed to learn the probability distributions of discourse functions of connectives from a small labeled dataset and a big unlabeled dataset. The statistics learned from the dataset demonstrates some interesting linguistic phenomena such as connective synonyms sharing similar distributions, multiple discourse functions of connectives, and couple-linking elements providing strong clues for discourse relation resolution.
Type
conference paper