Seminar on Research related to NLP

For more info: Research-presentation-related-in-NLP

This seminar was presented by Ash. The summary of this seminar is as follows.

***Peeking Into The Seminar***

This seminar was about large Corpus-based automatic grammar rules and export methods for information. There are two types.

1. Edit : A broad-coverage grammar checker using grammar pattern recognition.

example)

2. Information extraction from Web-scale N-gram data

example)

is(Laden, terrorist) – two words are connected with ‘is’

partOf(Laden,zihard) – a word connotes another word in two words

hasProperty(Laden,cruelty) – a word modifies the other word in two words.

For editing purposes, as the real purpose of this is editing sentences, it is used to edit a user’s sentences by exporting accurate grammar patterns. Therefore, there is no contribution from the information and relationship between words and sentences. In opposite, N-gram is about finding relationships among words and links to patterns. Only exporting patterns and relationships from large amounts of data, it can’t be used for other purpose. Furthermore, the grammar pattern correction in the future edits will drive and complete the system to correct paragraphs, pages, and text for the whole body of work. N-gram is expected to complete practicable programs which can draw relationships between words and various word relationships, inducing a complex interaction formula and improving the existing limitations. Through combining these two ways, grammar pattern collection has to be done by exporting the relationships and patterns between words and sentences among substantial amounts of data. Then, the editing system would be completed which can then be used to edit the user’s sentences, paragraphs, and complete writings automatically.