Multilingual entity task (MET)

Abstract

Japanese was one of the languages selected for evaluation of named entity identification algorithms in the TIPSTER-sponsored Multilingual Entity Task (MET) program. As with the Spanish and Chinese groups (Table 1), Japanese systems automatically marked the names of organizations, people, and places within entity name expressions (ENAMEX), dates and times within time expressions (TIMEX), and percents and money within number expressions (NUMEX). The participant Japanese systems were developed in a fourmonth period of time and output results comparable to the Message Understanding Conference-6 (MUC-6) [1] English language systems with F-Measures between 70 -90% [21.

Named entity chunking techniques in supervised learning for Japanese named entity recognition

“…In the . }al)anese lan-guage~ several recent conferences, such as MET (Multilingual Entity Task, MET-I (Maiorano, 1996) and MET-2 (MUC, 1998)) and IREX (Information l{etriew~l and Extraction Exercise) Workshop (IREX Committee, 1999), focused on named entity recognition ms one of their contest tasks, thus promoting research on Jat)anese named entity recognition.…”

The multilingual entity task (MET) overview

“…Across languages the keywords "press conference" retrieved a rich subcorpus of texts, covering a wide spectrum of topics. Frequency and types of expressions vary in the three language sets [2] [8] [9]. The original task guidelines were modified so that the core guidelines were language independent with language specific rules appended.…”