作者: Elisabetta Fersini , Enza Messina
DOI: 10.1007/978-3-642-37247-6_26
关键词:
摘要: The progressive deployment of ICT technologies in the courtroom is leading to development integrated multimedia folders where entire trial contents (documents, audio and video recordings) are available for online consultation via web-based platforms. current amount unstructured textual data into judicial domain, especially related hearing transcriptions, highlights therefore need automatically extract structured from ones improving efficiency processes. In this paper we address problem extracting information transcriptions generated using an ASR (Automatic Speech Recognition) system, by integrating Conditional Random Fields with background information. computational experiments show promising results structuring outputs, enabling a robust efficient document consultation.