Enhancing Semantic Search with BERT: An
Extended Approach
Batch Members :- Under Guidance Of :-
• S.MADHU:- 213J1A05F8 Dr.D.V.Divakar Rao
• R.DURGESHWANT :-213J1A05E5 Computer Science And
• S.K.P.MASTAN VALI :- 213J1A05G2 Engineering Department
• P.RAJEEV :- 213J1A05D9
Content
INTRODUCTION
PROBLEM STATEMENT
OBJECTIVES
LITERATURE REVIE
METHODOLOGY
SYSTEM ARCHITECTURE
UNIQUE CONTIBUTION TOWARDS OUR PROJECT
Relevance of BERT in Semantic
INTRODUCTION Search:
What is Semantic Search ? Contextual Understanding:
Definition: Search based in the Grasping word meaning based on
context and meaning of queries, surrounding words.
not just keywords Better Query Interpretation:
Importance of Semantic Search in Accurately understands complex,
Information Retrieval: conversational queries.
Handles Synonyms: Retrieves
Enhanced Accuracy: Understands
the meaning and context of relevant results even without
queries, not just keywords. exact keywords.
Improved Ranking: Prioritizes
Better Relevance: Handles
synonyms and variations, contextually relevant information.
returning relevant results even if
exact terms are missing.
Reduced Irrelevant Results:
Focuses on topic relevance over
mere keyword presence.
PROBLEM STATEMENT
Limitations of Traditional Keyword-Based Search:
Lacks Context: Only matches exact words, missing
meaning.
Synonym Issues: Can't handle variations or
synonyms.
Ambiguity: Struggles with multiple meanings.
Poor Query Interpretation: Fails with complex or
conversational queries.
Irrelevant Results: Often retrieves unrelated
content.
Need for Advanced Semantic Understanding:
Accurate Query Interpretation: Grasp intent, not
just keywords.
Context Awareness: Understand word meanings in
context.
Better Relevance: Handle synonyms and
variations.
Reduce Ambiguity: Resolve multiple meanings of
words.
Enhanced User Experience: Deliver precise,
relevant results
OBJECTIVES
TITLE OF THE PAPER :-
“MRI-Based Brain Tumor Classification With Ensemble Learning Techniques”
Author’s Name:-
Shobana & Balakrishnan
Shanmugapriya et al.
Singh
YEAR OF PUBLICATION :- 2023
KEY FINDING OR CONTRIBUTIONS:-
References
1. Bondy, M.L.; Scheurer, M.E.; Malmer, B.; Barnholtz-Sloan, J.S.; Davis, F.G.; Il’Yasova, D.;
Brain Tumor Epidemiology Consortium.
Brain tumor epidemiology: Consensus from the Brain Tumor Epidemiology Consortium.
Cancer 2008, 113, 1953–1968. [CrossRef]
[PubMed]
2. Sultan, H.H.; Salem, N.M.; Al-Atabany, W. Multi-classification of brain tumor images using
deep neural network. IEEE Access
2019, 7, 69215–69225. [CrossRef]
3. Paul, J.S.; Plassard, A.J.; Landman, B.A.; Fabbri, D. Deep learning for brain tumor
classification. In Medical Imaging 2017: Biomedical
Applications in Molecular, Structural, and Functional Imaging; International Society for
Optics and Photonics: Bellingham, WA, USA,
2017; Volume 10137, p. 1013710.
4. Shobana, G.; Balakrishnan, R. Brain tumor diagnosis from MRI feature analysis-A
comparative study. In Proceedings of the 2015
International Conference on Innovations in Information, Embedded and Communication
Systems (ICIIECS), Coimbatore, India,
19–20 March 2015; pp. 1–4.
5. Shanmugapriya, B.; Ramakrishnan, T. Segmentation of brain tumors in computed
tomography images using SVM classifier. In
Proceedings of the 2014 International Conference on Electronics and Communication
Systems (ICECS), Coimbatore, India, 13–14
February 2014; pp. 1–3.
THANK YOU
