R. Priyadharshini, G. Jeyakodi, P. Shanthi Bala
Research Cell: An International Journal of Engineering Science, Special Issue March 2023, Vol. 35,
A Peer reviewed and refreed journal, UGC Approved Journal (S.No.63019) (till May 2018)
ISSN: 2229-6913(Print), ISSN: 2320-0332(Online), Web Presence: http://ijoe.vidyapublications.com
© 2023 Vidya Publications
75
Comparative Analysis of Contextual Relation
Extraction based on Deep Learning Models
1
R. Priyadharshini,
2
G. Jeyakodi,
3
P. Shanthi Bala
Department of Computer Science, School of Engineering and Technology, Pondicherry
University, Puducherry, India
1
priyadharsini.r02@gmail.com,
2
rjeyakodi02@gmail.com,
3
shanthibala.cs@gmail.com
ABSTRACT
Contextual Relation Extraction (CRE) is mainly used for constructing a knowledge
graph with a help of ontology. It performs various tasks such as semantic search, query
answering, and textual entailment. Relation extraction identifies the entities from raw
texts and the relations among them. An efficient and accurate CRE system is essential
for creating domain knowledge in the biomedical industry. Existing Machine Learning
and Natural Language Processing (NLP) techniques are not suitable to predict complex
relations from sentences that consist of more than two relations and unspecified entities
efficiently. In this work, deep learning techniques have been used to identify the
appropriate semantic relation based on the context from multiple sentences. Even though
various machine learning models have been used for relation extraction, they provide
better results only for binary relations, i.e., relations occurred exactly between the two
entities in a sentence. Machine learning models are not suited for complex sentences that
consist of the words that have various meanings. To address these issues, hybrid deep
learning models have been used to extract the relations from complex sentence
effectively. This paper explores the analysis of various deep learning models that are
used for relation extraction.
KEYWORDS: Contextual Relation Extraction, Word Embeddings, BERT,
Deep Learning Model.
INTRODUCTION
Contextual Relation Extraction (CRE) helps to understand the meaning of the entities
and their relationship in a sentence. It can improve the performance of Natural
Language Processing tasks such as information retrieval, question answering, and
semantic search [1]. Named Entity Recognition aims to automatically identify and
classify objects like people, products, organizations, locations, etc. The process of
identifying the terms in a text and arranging in an appropriate group is a source for
named entity recognition and a key component for text analysis. The analysis of common
syntactic patterns is an important factor of NER. Many deep learning models solve
entity recognition applications such as indexing documents, finding relationship among
entities, and building an ontology [2-4]. The combination of NER and CRE can provide
a rich understanding of the text by identifying both the entities and their relationships
based on the context. The joint modeling of entity recognition and relation classification