Motivations and Methods for Text Simplication

Long and complicated sentences prove to be a stumbling block for current systems relying on NL input. These systems stand to gain from methods that syntactically simplify such sentences. To simplify a sentence, we need an idea of the structure of the sentence, to identify the components to be separated out. Obviously a parser could be used to obtain the complete structure of the sentence. However, full parsing is slow and prone to failure, especially on complex sentences. In this paper, we consider two alternatives to full parsing which could be used for simpli cation. The rst approach uses a Finite State Grammar (FSG) to produce noun and verb groups while the second uses a Supertagging model to produce dependency linkages. We discuss the impact of these two input representations on the simpli cation process. 1 Reasons for Text Simpli cation Long and complicated sentences prove to be a stumbling block for current systems which rely on natural language input. These systems stand to gain from methods that preprocess such sentences so as to make them simpler. Consider, for example, the following sentence: (1) The embattled Major government survived a crucial vote on coal pits closure as its last-minute concessions curbed the extent of Tory revolt over an issue that generated unusual heat in the House of Commons and brought the miners to London streets. Such sentences are not uncommon in newswire texts. Compare this with the multi-sentence version which has been manually simpli ed: (2) The embattled Major government survived a crucial vote on coal pits closure. Its last-minute concessions curbed the extent of On leave from the National Centre for Software Technology, Gulmohar Cross Road No. 9, Juhu, Bombay 400 049, India Tory revolt over the coal-mine issue. This issue generated unusual heat in the House of Commons. It also brought the miners to