Information Retrieval is a well established interdisciplinary topic in which machine learning, computational linguistic, computer programming and data mining merge together. SLAIR stands for SeaLab Advanced Information Retrieval and is an efficient software architecture that embeds these issues in a unique framework. SLAIR is expandable both from the data format and algorithm point of view. A pluggable notion of distance between documents drives the subsequent clustering/classification machinery; moreover SLAIR is explicitly designed to manage large scale text mining problems. The demo will be focused on the versatility of the framework; the main goal is to show how the different metrics provided by SLAIR can enhance clustering/classification ability and eventually lead to different views of the underlying textual data
SeaLab Advanced Information Retrieval
GASTALDO, PAOLO;ZUNINO, RODOLFO
2010-01-01
Abstract
Information Retrieval is a well established interdisciplinary topic in which machine learning, computational linguistic, computer programming and data mining merge together. SLAIR stands for SeaLab Advanced Information Retrieval and is an efficient software architecture that embeds these issues in a unique framework. SLAIR is expandable both from the data format and algorithm point of view. A pluggable notion of distance between documents drives the subsequent clustering/classification machinery; moreover SLAIR is explicitly designed to manage large scale text mining problems. The demo will be focused on the versatility of the framework; the main goal is to show how the different metrics provided by SLAIR can enhance clustering/classification ability and eventually lead to different views of the underlying textual data
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
