Work

Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings

Year: 2019

Type: conference-paper

Abstract: It has been shown that implicit connectives can be exploited to improve the performance of the models for implicit discourse relation recognition (IDRR).An important property of the implicit connectives is that they can be accurately mapped into the discourse relations conveying their functions.In this work, we explore this property in a multi-task learning framework for IDRR in which the relations and the connectives are simultaneously predicted, and the mapping is leveraged to transfer knowledge between the two prediction tasks via the embeddings of relations and connectives.We propose several techniques to enable such knowledge transfer that yield the state-of-the-art performance for IDRR on several settings of the benchmark dataset (i.e., the Penn Discourse Treebank dataset).

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/p19-1411

Authors: Linh The Nguyen, Linh Van Ngo, Khoat Than, Thien Huu Nguyen

Institutions: Trường Đại học Khoa học và Công nghệ Hà Nội, Hanoi University of Science and Technology, University of Oregon

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Asian Office of Aerospace Research and Development, Office of Naval Research, Air Force Office of Scientific Research, Office of Naval Research Global

Awards: G3981288785, G6297490666, G8790200492