Time expression extraction from free text

In this contemporary cyber era, time plays a very important role. We can see different time formats all over the world. It is hard for reader to identify the date or time in the text with the publish date. The purpose of this project to analysis and extract time expressions from free text. We ana...

Full description

Saved in:
Bibliographic Details
Main Author: Deng, Xi Yu
Other Authors: Sun Aixin
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/76992
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:In this contemporary cyber era, time plays a very important role. We can see different time formats all over the world. It is hard for reader to identify the date or time in the text with the publish date. The purpose of this project to analysis and extract time expressions from free text. We analyze three different datasets and perform normalization on each of them. Based on the findings, we purpose a typebased approach named Mytime. In recognition, Mytime will firstly identify related keywords from free text then search the next few words to finalize the time phase and finally it will perform normalization to generate the updated date and time accordingly. Mytime runs in real time and can be easily expanded by adding in different language libraries.