Developing and applying an integrated semantic framework for natural language understanding

The standard approach in Natural Language Processing for semantic analysis (Word-Sense Disambiguation, Named-Entity Recognition and other related tasks) is to match tokens from shallow parsed text (tokenized, POS tagged, shallow trunking, et cetera) to a sense repository and then rank them to find t...

Full description

Saved in:
Bibliographic Details
Main Author: Le, Tuan Anh
Other Authors: Francis Bond
Format: Theses and Dissertations
Language:English
Published: 2019
Subjects:
Online Access:https://hdl.handle.net/10356/89208
http://hdl.handle.net/10220/49370
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-89208
record_format dspace
spelling sg-ntu-dr.10356-892082020-10-15T06:28:19Z Developing and applying an integrated semantic framework for natural language understanding Le, Tuan Anh Francis Bond School of Humanities Humanities::Linguistics::Sociolinguistics::Computational linguistics Humanities::Linguistics::Semantics The standard approach in Natural Language Processing for semantic analysis (Word-Sense Disambiguation, Named-Entity Recognition and other related tasks) is to match tokens from shallow parsed text (tokenized, POS tagged, shallow trunking, et cetera) to a sense repository and then rank them to find the best candidates. This practice has yet to exploit the extra information that is available in structural semantics, which can be accessed using deep grammars. This dissertation proposes the Integrated Semantic Framework, a novel method to improve computational semantic analysis by providing both structural semantics from construction grammars and lexical semantics from ontologies in a single representation. The method was implemented as a software package that produces computational semantic analysis and its performance was compared to human annotators and some others semantic analysis systems on a short story. Currently, the implemented system only provides analyses for standard English texts. However the design is extensible to other languages and is already being developed for the Japanese language. Finally, although the implemented system is still a prototype (most rules are generated automatically, the structure matching and transforming features are still at a basic level, and a few other tasks remain on the to-improve list), the results prove that such a system can be built and can produce positive results. This research demonstrated that it is possible to provide a more natural and sophisticated computational semantic analysis. It aims to motivate linguists to join the development of fundamental semantic theories in the field of Natural Language Processing; to interpret and provide better semantics that exist in natural languages. Doctor of Philosophy 2019-07-16T06:03:16Z 2019-12-06T17:20:16Z 2019-07-16T06:03:16Z 2019-12-06T17:20:16Z 2019 Thesis https://hdl.handle.net/10356/89208 http://hdl.handle.net/10220/49370 10.32657/10220/49370 en 189 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Humanities::Linguistics::Sociolinguistics::Computational linguistics
Humanities::Linguistics::Semantics
spellingShingle Humanities::Linguistics::Sociolinguistics::Computational linguistics
Humanities::Linguistics::Semantics
Le, Tuan Anh
Developing and applying an integrated semantic framework for natural language understanding
description The standard approach in Natural Language Processing for semantic analysis (Word-Sense Disambiguation, Named-Entity Recognition and other related tasks) is to match tokens from shallow parsed text (tokenized, POS tagged, shallow trunking, et cetera) to a sense repository and then rank them to find the best candidates. This practice has yet to exploit the extra information that is available in structural semantics, which can be accessed using deep grammars. This dissertation proposes the Integrated Semantic Framework, a novel method to improve computational semantic analysis by providing both structural semantics from construction grammars and lexical semantics from ontologies in a single representation. The method was implemented as a software package that produces computational semantic analysis and its performance was compared to human annotators and some others semantic analysis systems on a short story. Currently, the implemented system only provides analyses for standard English texts. However the design is extensible to other languages and is already being developed for the Japanese language. Finally, although the implemented system is still a prototype (most rules are generated automatically, the structure matching and transforming features are still at a basic level, and a few other tasks remain on the to-improve list), the results prove that such a system can be built and can produce positive results. This research demonstrated that it is possible to provide a more natural and sophisticated computational semantic analysis. It aims to motivate linguists to join the development of fundamental semantic theories in the field of Natural Language Processing; to interpret and provide better semantics that exist in natural languages.
author2 Francis Bond
author_facet Francis Bond
Le, Tuan Anh
format Theses and Dissertations
author Le, Tuan Anh
author_sort Le, Tuan Anh
title Developing and applying an integrated semantic framework for natural language understanding
title_short Developing and applying an integrated semantic framework for natural language understanding
title_full Developing and applying an integrated semantic framework for natural language understanding
title_fullStr Developing and applying an integrated semantic framework for natural language understanding
title_full_unstemmed Developing and applying an integrated semantic framework for natural language understanding
title_sort developing and applying an integrated semantic framework for natural language understanding
publishDate 2019
url https://hdl.handle.net/10356/89208
http://hdl.handle.net/10220/49370
_version_ 1681056463305310208