Work

Using phrasal patterns to identify discourse relations

Year: 2006

Type: conference-paper

Abstract: This paper describes a system which identifies discourse relations between two successive sentences in Japanese. On top of the lexical information previously proposed, we used phrasal pattern information. Adding phrasal information improves the system's accuracy 12%, from 53% to 65%.

DOI: 10.3115/1614049.1614083

Authors: Manami Saito, Kazuhide Yamamoto, Satoshi Sekine

Institutions: Nagaoka University of Technology, New York University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funders: National Science Foundation, York University

OpenAlex ID: W2034087555

FWCI: 0.971

Cites: 2

Cited by: 36

Related to: 10