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.- Anthology ID:
- R17-1042
- Volume:
- Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
- Month:
- September
- Year:
- 2017
- Address:
- Varna, Bulgaria
- Venue:
- RANLP
- SIG:
- Publisher:
- INCOMA Ltd.
- Note:
- Pages:
- 309–315
- Language:
- URL:
- https://doi.org/10.26615/978-954-452-049-6_042
- DOI:
- 10.26615/978-954-452-049-6_042
- Cite (ACL):
- Sohail Hooda and Leila Kosseim. 2017. Argument Labeling of Explicit Discourse Relations using LSTM Neural Networks. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 309–315, Varna, Bulgaria. INCOMA Ltd..
- Cite (Informal):
- Argument Labeling of Explicit Discourse Relations using LSTM Neural Networks (Hooda & Kosseim, RANLP 2017)
- PDF:
- https://doi.org/10.26615/978-954-452-049-6_042