Expanding a multilingual media monitoring and information extraction tool to a new language: Swahili

• Published in: Language Resources and Evaluation Vol. 45; no. 3; pp. 311 - 330
• Main Authors: Steinberger, Ralf, Ombuya, Sylvia, Kabadjov, Mijail, Pouliquen, Bruno, Rocca, Leo Della, Belyaeva, Jenya, de Paola, Monica, Ignat, Camelia, van der Goot, Erik
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer 01.09.2011; Springer Netherlands; Springer Nature B.V
• Subjects: African languages; Bantu languages; Classification; Clustering; Computational Linguistics; Computer Applications; Computer Generated Language Analysis; Computer Science; Computer software; Dictionaries; Information management; Information retrieval; Language and Literature; Languages; Legal entities; Linguistics; Media; Monitoring; Multilingualism; Names; Nonnative languages; Nouns; Original Paper; Recognition; Reported Speech; Social Sciences; Speech; Speech recognition; Strapping; Swahili; Swahili language; Text Analysis; Text analytics; Texts; Verbs; Words; Italy; Netherlands; United States > US; Europe; Date recognition; Subject domain classification; Geo-tagging; Quotation recognition; News analysis; Swahili; Information extraction; Multilinguality; Named entity recognition and classification; Media monitoring
• ISSN: 1574-020X; 1572-8412; 1574-0218
• DOI: 10.1007/s10579-011-9155-y

The Europe Media Monitor (EMM) family of applications is a set of multilingual tools that gather, cluster and classify news in currently fifty languages and that extract named entities and quotations (reported speech) from twenty languages. In this paper, we describe the recent effort of adding the African Bantu language Swahili to EMM. EMM is designed in an entirely modular way, allowing plugging in a new language by providing the language-specific resources for that language. We thus describe the type of language-specific resources needed, the effort involved, and ways of boot-strapping the generation of these resources in order to keep the effort of adding a new language to a minimum. The text analysis applications pursued in our efforts include clustering, classification, recognition and disambiguation of named entities (persons, organisations and locations), recognition and normalisation of date expressions, as well as the identification of reported speech quotations by and about people.