“…The application of NLP to texts involves a sequence of analytical tasks performed in the separate modules that constitute the linguistic architecture of the system. Among available tools for NP extraction are: the category tagger based on Brill's (1992) rules; the Xerox morphological analyzer (Karttunen, Kaplan, & Zaenen, 1992); disambiguation devices of POS categories based on stochastic methods, such as the hidden Markov model (HMM) (Cutting, Kupiec, Pedersen, & Sibun, 1992;Kupiec, 1992Kupiec, , 1993; the NPtool phrase analyzer (Voutilainen, 1997); or the AZ noun phraser (Tolle & Chen, 2000), which combines tokenizing with POS tagging (Brill, 1993).…”