Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Neuro-Symbolic Word Embedding Using Textual and Knowledge Graph Informationopen access

Authors
Oh, DongsukLim, JungwooLim, Heuiseok
Issue Date
10월-2022
Publisher
MDPI
Keywords
neuro-symbolic; graph convolutional network; word embedding; dependency parsing; semantic role labeling; ConceptNet; external knowledge
Citation
APPLIED SCIENCES-BASEL, v.12, no.19
Indexed
SCIE
SCOPUS
Journal Title
APPLIED SCIENCES-BASEL
Volume
12
Number
19
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/145524
DOI
10.3390/app12199424
ISSN
2076-3417
Abstract
The construction of high-quality word embeddings is essential in natural language processing. In existing approaches using a large text corpus, the word embeddings learn only sequential patterns in the context; thus, accurate learning of the syntax and semantic relationships between words is limited. Several methods have been proposed for constructing word embeddings using syntactic information. However, these methods are not trained for the semantic relationships between words in sentences or external knowledge. In this paper, we present a method for improved word embeddings using symbolic graphs for external knowledge and the relationships of the syntax and semantic role between words in sentences. The proposed model sequentially learns two symbolic graphs with different properties through a graph convolutional network (GCN) model. A new symbolic graph representation is generated to understand sentences grammatically and semantically. This graph representation includes comprehensive information that combines dependency parsing and semantic role labeling. Subsequently, word embeddings are constructed through the GCN model. The same GCN model initializes the word representations that are created in the first step and trains the relationships of ConceptNet using the relationships between words. The proposed word embeddings outperform the baselines in benchmarks and extrinsic tasks.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Computer Science and Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE