China
Africa
Explore chapters and articles related to this topic
Automated Rule-Based Checking Systems
Published in Nawari O. Nawari, Building Information Modeling, 2018
Currently, NLP employs various probabilistic and data-driven models. Algorithms for parsing, part-of-speech tagging, reference resolutions, and discourse processing all began to incorporate probabilistic and neural network principles as well as evolution strategies from speech recognition and information retrieval. It is in essence an interdisciplinary area where computational linguistics combine with AI. NLP utilizes AI tools such as algorithms, data structures, formal models of knowledge representations, models for reasoning processes, and so on. The goal of NLP is to specify language comprehension and production theory to such a level of detail that a person and a machine can communicate naturally. Some of the major tasks of the NLP system include language reading and writing; automatic summarization; voice and character recognition; IE; IR, which is concerned with storing, searching, and retrieving information; machine translation; translation from one language into another; natural language generation; natural language understanding; spoken dialog system; text-to-speech; text proofing; and text simplification.
Studying the Effect of Syntactic Simplification on Text Summarization
Published in IETE Technical Review, 2023
Niladri Chatterjee, Raksha Agarwal
Transformations based on the syntactic structure of the sentence have been utilized for performing text simplification by many different works in literature. These include transformation rules using typed dependency representations [26] and synchronous dependency grammars [27]. Ferres et al. [28] and Scranton et al. [29] used dependency parse structure, while Garin et al. [30] used constituency parse trees to perform simplification transformations. Evans and Orason [31] used a sign tagger to identify compound clauses and rule-based transformations for rewriting.