Work

Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither

Year: 2010

Type: conference-paper

Abstract: The term Morphologically Rich Languages (MRLs) refers to languages in which signif-icant information concerning syntactic units and relations is expressed at word-level. There is ample evidence that the application of read-ily available statistical parsing models to such languages is susceptible to serious perfor-mance degradation. The first workshop on sta-tistical parsing of MRLs hosts a variety of con-tributions which show that despite language-specific idiosyncrasies, the problems associ-ated with parsing MRLs cut across languages and parsing frameworks. In this paper we re-view the current state-of-affairs with respect to parsing MRLs and point out central chal-lenges. We synthesize the contributions of re-searchers working on parsing Arabic, Basque, French, German, Hebrew, Hindi and Korean to point out shared solutions across languages. The overarching analysis suggests itself as a source of directions for future investigations. 1

Source: Arrow@dit (Dublin Institute of Technology)

Authors: Reut Tsarfaty, Djamé Seddah, Yoav Goldberg, Sandra Kuebler, Yannick Versley, Marie Candito, Jennifer Foster, Ines Rehbein, Lamia Tounsi

Institutions: Uppsala University, Institut national de recherche en sciences et technologies du numérique, Paris-Sorbonne University, Ben-Gurion University of the Negev, Indiana University, University of Tübingen, Dublin City University, Saarland University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Institut national de recherche en informatique et en automatique (INRIA)

OpenAlex ID: W2109000768

FWCI: 8.023

Cites: 60

Cited by: 96

Related to: 20