Capturing relations for understanding spatial dynamics from unstructured text

Authors: Chen-Chieh Feng*, Geography, National University of Singapore
Topics: Geographic Information Science and Systems, Temporal GIS, Quantitative Methods
Keywords: relations, semantics, spatial dynamics, digital humanity
Session Type: Paper
Day: 4/4/2019
Start / End Time: 8:00 AM / 9:40 AM
Room: Capitol Room, Omni, East
Presentation File: No File Uploaded

Capturing relations between various entities in texts, including persons, artifacts, as well as their locations and movements, to support reasoning tasks has been an invaluable means for understanding all sorts of dynamics between them. In addition to relations traditionally being captured, such as kinship and business relations, the space and place where interactions and events occurred provide the context within which richer semantics can be extracted and more accurate reasoning can be obtained. Previous work on extracting such relations from texts have been relying on pattern matching approaches. With the aid of existing bibliographic and point-of-interest databases, such approaches have achieved some level of success. Yet, the results remain unsatisfactory compared to the results obtained by human operators. This study expands from our previous study and explores how natural language processing (NLP) tools may improve relation extraction results. The text from Famous Historical Figures of Singaporean Chinese will be used. The presentation will report the experience of using NLP tools for the stated purpose and how it advances automatic extraction of relations for supporting digital humanity applications.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login