The CLaC Discourse Parser at CoNLL-2015

TL;DR

This paper presents a discourse parser developed using UIMA and ClearTK, achieving a 17.3 F1 score on the CoNLL-2015 shared task, demonstrating its effectiveness in shallow discourse parsing.

Contribution

The paper introduces a UIMA-based discourse parser with machine learning integration for the CoNLL-2015 shared task, ranking sixth with a 17.3 F1 score.

Findings

Achieved 17.3 F1 score on the test set

Ranked sixth in the shared task

Demonstrated effectiveness of UIMA and ClearTK in discourse parsing

Abstract

This paper describes our submission (kosseim15) to the CoNLL-2015 shared task on shallow discourse parsing. We used the UIMA framework to develop our parser and used ClearTK to add machine learning functionality to the UIMA framework. Overall, our parser achieves a result of 17.3 F1 on the identification of discourse relations on the blind CoNLL-2015 test set, ranking in sixth place.