In this paper, we are concerned with the problem of automatic template creation for Information Extraction (IE) and we present a methodology for the creation of IE templates. Our approach proposes the semi-automatic construction of a semantic representation of textual information based on recognition of multi-word and nested terms and Named Entities (NEs) and subsequent exploitation of term and NE context for the induction of Information Extraction template rules.
|Title of host publication||Natural Language Processing|
|Subtitle of host publication||Second International Conference Patras, Greece, June 2–4, 2000 Proceedings|
|Place of Publication||Heidelberg|
|ISBN (Electronic)|| 978-3-540-45154-9|
|Publication status||Published - 2000|
|Name||Lecture Notes in Computer Science|