Argument Labeling of Explicit Discourse Relations using LSTM Neural Networks

TL;DR

This paper introduces an LSTM-based model for argument labeling in explicit discourse relations that learns from raw data, outperforming previous RNN approaches but still below feature-based systems, with broader applicability.

Contribution

The paper presents a novel LSTM model for argument labeling that requires no feature engineering, improving over prior RNN methods and enhancing applicability across genres and languages.

Findings

Achieved 23.05% F1 on PDTB dataset with LSTM model.

Outperformed previous RNN approach (20.52% F1).

Less accurate than feature-based systems but more versatile.

Abstract

Argument labeling of explicit discourse relations is a challenging task. The state of the art systems achieve slightly above 55% F-measure but require hand-crafted features. In this paper, we propose a Long Short Term Memory (LSTM) based model for argument labeling. We experimented with multiple configurations of our model. Using the PDTB dataset, our best model achieved an F1 measure of 23.05% without any feature engineering. This is significantly higher than the 20.52% achieved by the state of the art RNN approach, but significantly lower than the feature based state of the art systems. On the other hand, because our approach learns only from the raw dataset, it is more widely applicable to multiple textual genres and languages.