Work

Handling Unknown Words in Statistical Latent-Variable Parsing Models for Arabic, English and French

Year: 2010

Type: conference-paper

Abstract: This paper presents a study of the impact of using simple and complex morphological clues to improve the classification of rare and unknown words for parsing. We compare this approach to a language-independent technique\noften used in parsers which is based solely on word frequencies. This study is applied to three languages that exhibit different levels of morphological expressiveness: Arabic, French and English. We integrate information\nabout Arabic affixes and morphotactics into a PCFG-LA parser and obtain stateof-the-art accuracy. We also show that these morphological clues can be learnt automatically\nfrom an annotated corpus.

Source: Arrow@dit (Dublin Institute of Technology)

Authors: Attia, Mohammed, Foster, Jennifer, Hogan, Deirdre, Le Roux, Joseph, Tounsi, Lamia, van Genabith, Josef

Institution: Dublin City University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Enterprise Ireland, Irish Research Council for Science, Engineering and Technology, Irish Research Council

OpenAlex ID: W2132890663

FWCI: 6.718

Cites: 21

Cited by: 47

Related to: 10