Abstract

This paper describes a novel approach for the task of end-to-end argument labeling in shallow discourse parsing. Our method describes a decomposition of the overall labeling task into subtasks and a general distance-based aggregation procedure. For learning these subtasks, we train a recurrent neural network and gradually replace existing components of our baseline by our model. The model is trained and evaluated on the Penn Discourse Treebank 2 corpus. While it is not as good as knowledge-intense approaches, it clearly outperforms other models that are also trained without additional linguistic features.

Highlights

  • Shallow discourse parsing (SDP) is a challenging problem in NLP with the aim to identify local coherence relations in text

  • The first experiment is a simplification of the general argument labeling problem, where a connective has already been classified

  • We use precision, recall, and F1 score of exact matches, in order to be comparable with the previous work

Read more

Summary

Introduction

Shallow discourse parsing (SDP) is a challenging problem in NLP with the aim to identify local coherence relations in text. Discourse relations are used in text to connect individual segments of text logically. The Penn Discourse Treebank (PDTB) (Prasad et al, 2008a) adopts a nonhierarchical view on discourse relations. Contains an explicit discourse relation which is signaled through the underlined connective (Conn) and further consists of two arguments (Arg in italics and Arg in bold). Does not work on a sentence-level, but takes full documents into account. Short paragraphs suffice to show the challenge in extracting overlapping relations. Though our implementation works on the level of individual to-

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.