EVOLUTIONARY SHALLOW NATURAL LANGUAGE PARSING

Identifying syntactical information from natural‐language texts requires the use of sophisticated parsing techniques mainly based on statistical and machine‐learning methods. However, due to complexity and efficiency issues many intensive natural‐language processing applications using full syntactic analysis methods may not be effective when processing large amounts of natural‐language texts. These tasks can adequately be performed by identifying partial syntactical information through shallow parsing (or chunking) techniques. In this work, a new approach to natural‐language chunking using an evolutionary model is proposed. It uses previously captured training information to guide the evolution of the model. In addition, a multiobjective optimization strategy is used to produce unique quality values for objective functions involving the internal and the external quality of chunking. Experiments and the main results obtained using the model and state‐of‐the‐art approaches are discussed.