Text Simplification by A. SIddharthan

Syntactic Simplification and Text Cohesion.

Definition of Syntactic simplificaiton: reducing the grammatical complexity without at all changing it's meaning unlike the Gene replacement with tags and noun phrase replacement with heads. Useful for parsers and also for helping people with reading disabilities. In the future can be used in clinical domain.

Can also be used for machine translation apart from parsing - performance decreases dramatically with the sentence length.

Orignally, :( unfortunately not my innovation, the idea of Chandrasekharan(1996 and 1997) to use it as a preprocessor for parsers, but they don't pay much attention to text cohesiveness which is important even in applications that deal with sentence level.

Example:
Mr. Anthony, who runs an employment agency, decries program trading,but he isn’t sure it should be strictly regulated.

Mr. Anthony decries program trading. Mr. Anthony runs an employment agency. But he isn’t sure it should be strictly regulated.

Adverse effect on conjunctive(but) cohesion and anaphoric cohesion. Paper Contribution: Shows that both can be handled independently.

Example for an anaphoric cohesion independent of conjunctive cohesion:
Dr. Knudson found that some children with the eye cancer had inherited a damaged copy of chromosome No. 13 from a parent, who had necessarily had the disease. Under a microscope he could actually see that a bit of chromosome 13 was missing.

Dr. Knudson found that some children with the eye cancer had inherited a damaged copy of chromosome No. 13 from a parent. This parent had necessarily had the disease. Under a microscope he could actually see that a bit of chromosome 13 was missing.




LT Text Tokenization Toolkit (Grover et al., 2000) to perform the initial analysis – segmenting text into sentences, annotating words with their part-of-speech tags and marking up noun chunks.

syntactic structures that can be simplified in each sentence: clause/appositive identification and clause/appositive attachment. Details: Siddharthan 2002, 2003a,b). Here there is a potential of using Biological dictionaries. This makes it different from ordinary english.