tailieunhanh - Báo cáo khoa học: "Generalised PP-Attachment Disambiguation using Corpus-based Linguistic Diagnostics"

We propose a new formulation of the PP attachment problem as a 4-way classification which takes into account the argument or adjunct status of the PP. Based on linguistic diagnostics, we train a 4-way classifier that reaches an average accuracy of (baseline ). Compared to a sequence of binary classifiers, the 4-way classifier reaches better performance and individuates a verb's arguments more accurately, thus improving the acquisition of a crucial piece of information for many NLP applications. . | Generalised PP-Attachment Disambiguation using Corpus-based Linguistic Diagnostics Paola Merlo Linguistics Department University of Geneva 2 rue de Candolle 1211 Geneva 4 Switzerland merlo@ Abstract We propose a new formulation of the pp attachment problem as a 4-way classification which takes into account the argument or adjunct status of the pp Based on linguistic diagnostics we train a 4-way classifier that reaches an average accuracy of baseline . Compared to a sequence of binary classifiers the 4-way classifier reaches better performance and individuates a verb s arguments more accurately thus improving the acquisition of a crucial piece of information for many NLP applications. 1 Motivation Incorrect attachment of prepositional phrases often constitutes the main source of errors in current parsing systems. Correct attachment of PPs is necessary to construct a parse tree which will support the proper interpretation of constituents in the sentence. Consider the time-wom example I saw the man with the telescope It is important to determine if the pp with the telescope is to be attached as a sister to the noun the man restricting its interpretation or if it is to be attached to the verb thereby indicating the instrument of the main action described by the sentence. Based on examples of this sort recent approaches have formalised the problem of disambiguating pp attachments as a binary choice distinguishing between attachment of a pp to a given verb or to the verb s direct object Ratnaparkhi et al. 1994 Collins and Brooks 1995 . This is however a simplification of the problem which does not take the nature of the attachment into account. Precisely it does not distinguish pp arguments from pp adjuncts. Consider the following example which contains two PPs both modifying the verb. Put the block on the table in the morning The first pp is a locative pp required by the subcategorisation frame of the verb put while in the morning is an .