Multi-view and multi-task training of RST discourse parsers

TY - GEN

T1 - Multi-view and multi-task training of RST discourse parsers

AU - Braud, Chloé Elodie

AU - Plank, Barbara

AU - Søgaard, Anders

N1 - Conference code: 26

PY - 2016

Y1 - 2016

N2 - We experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat this by regularizing our models using task supervision from related tasks as well as alternative views on discourse structures. We show that a simple LSTM sequential discourse parser takes advantage of this multi-view and multi-task framework with 12-15% error reductions over our baseline (depending on the metric) and results that rival more complex state-of-the-art parsers.

AB - We experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat this by regularizing our models using task supervision from related tasks as well as alternative views on discourse structures. We show that a simple LSTM sequential discourse parser takes advantage of this multi-view and multi-task framework with 12-15% error reductions over our baseline (depending on the metric) and results that rival more complex state-of-the-art parsers.

M3 - Article in proceedings

SP - 1903

EP - 1913

BT - The 26th International Conference on Computational Linguistics

T2 - The 26th International Conference on Computational Linguistics

Y2 - 11 December 2016 through 16 December 2016

ER -