This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Jyoti Jayesh Chavhan,
Shoaib Hafiz Shaikh,
Suyash Kiran Ayachit,
Sheshasai Arjun Dusa,
Nivedh Vijay Anakakkil,
- Assistant Professor, Department of Artificial Intelligence Machine Learning, SIES Graduate School of Technology, Nerul, Navi-Mumbai, Maharashtra, India
- Student, Department of Artificial Intelligence Machine Learning, SIES Graduate School of Technology, Nerul, Navi-Mumbai, Maharashtra, India
- Student, Department of Artificial Intelligence Machine Learning, SIES Graduate School of Technology, Nerul, Navi-Mumbai, Maharashtra, India
- Student, Department of Artificial Intelligence Machine Learning, SIES Graduate School of Technology, Nerul, Navi-Mumbai, Maharashtra, India
- Student, Department of Artificial Intelligence Machine Learning, SIES Graduate School of Technology, Nerul, Navi-Mumbai, Maharashtra, India
Abstract document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_106515’);});Edit Abstract & Keyword
For knowledge-intensive businesses, large document libraries contain a plethora of information. Massive, chaotic and collections of documents that are unstructured have emerged from this rapid increase. Even if accessing or storing these documents have becomes easier, finding the required critical information in these vast document collections has become more difficult. NLP (Natural language processing) is one of the techniques use to retrieve the particular information that is required from a huge chunk of data. The proposed system uses cutting-edge methods for document comprehension and natural language processing to enable users to upload PDFs and ask questions and get timely, accurate answers. NLP techniques uses the subtle layers of context and semantics, going beyond simple keyword extraction. The interface facilitates easy interaction with complex textual material by providing users with access to a multitude of information. Regardless of your experience level, level of diligence, or role as a multi-disciplinary expert, the platform meets a wide range of needs and fluidly adjusts to meet each user’s specific needs. This initiative stands out as a pathfinder as we traverse the digital world, where information is plentiful but frequently difficult to extract. It not only makes it easier to interact with textual content, but it also creates an ecosystem where insights are easily available to everyone. It is evidence of how innovation can create a knowledge environment that is inclusive of all people and productive, paving the way for a genuinely inclusive digital age.
Keywords: NLP, user friendly, innovation, information retrieval, extraction
[This article belongs to International Journal of Computer Science Languages (ijcsl)]
Jyoti Jayesh Chavhan, Shoaib Hafiz Shaikh, Suyash Kiran Ayachit, Sheshasai Arjun Dusa, Nivedh Vijay Anakakkil. Advanced Document Query System. International Journal of Computer Science Languages. 2024; 02(02):-.
Jyoti Jayesh Chavhan, Shoaib Hafiz Shaikh, Suyash Kiran Ayachit, Sheshasai Arjun Dusa, Nivedh Vijay Anakakkil. Advanced Document Query System. International Journal of Computer Science Languages. 2024; 02(02):-. Available from: https://journals.stmjournals.com/ijcsl/article=2024/view=0
References
document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_106515’);});Edit
[1] Daniel Jurafsky, James H. Martin. Speech and Language Processing. 2024. Available from https://web.stanford.edu/~jurafsky/slp3/ed3bookaug20_2024.pdf
[2] Bird S, Klein E, Loper E. Natural language processing with Python: analyzing text with the natural language toolkit. ” O’Reilly Media, Inc.”; 2009 Jun 12.
[3] Manning, Christopher D. Introduction to information retrieval. 2008. New York : Cambridge University Press. https://archive.org/details/introductiontoin0000mann_b6m0
[4] Rahman N, Mozer R, McHugh RK, Rockett IR, Chow CM, Vaughan G. Using natural language processing to improve suicide classification requires consideration of race. Suicide and Life‐Threatening Behavior. 2022 Aug;52(4):782-91.
[5] Irfan S, Ghosh S. Optimization of information retrieval using evolutionary computation: A survey. In2017 International Conference on Computing, Communication and Automation (ICCCA) 2017 May 5 (pp. 328-333). IEEE.
[6] Ren J, Wang H, Liu T. Information retrieval based on knowledge-enhanced word embedding through dialog: A case study. International Journal of Computational Intelligence Systems. 2020 Jan;13(1):275-90.
[7] Dörpinghaus J, Stefan A. Optimization of Retrieval Algorithms on Large Scale Knowledge Graphs. In2020 15th Conference on Computer Science and Information Systems (FedCSIS) 2020 Sep 6 (pp. 227-236). IEEE.
8] Pan Z. Optimization of information retrieval algorithm for digital library based on semantic search engine. In2020 International conference on computer engineering and application (ICCEA) 2020 Mar 18 (pp. 364-367). IEEE.
[9] Ceri S, Bozzon A, Brambilla M, Della Valle E, Fraternali P, Quarteroni S. Web information retrieval. Springer Science & Business Media; 2013 Aug 30.
| Volume | 02 |
| Issue | 02 |
| Received | 27/06/2024 |
| Accepted | 08/09/2024 |
| Published | 07/10/2024 |
function myFunction2() {
var x = document.getElementById(“browsefigure”);
if (x.style.display === “block”) {
x.style.display = “none”;
}
else { x.style.display = “Block”; }
}
document.querySelector(“.prevBtn”).addEventListener(“click”, () => {
changeSlides(-1);
});
document.querySelector(“.nextBtn”).addEventListener(“click”, () => {
changeSlides(1);
});
var slideIndex = 1;
showSlides(slideIndex);
function changeSlides(n) {
showSlides((slideIndex += n));
}
function currentSlide(n) {
showSlides((slideIndex = n));
}
function showSlides(n) {
var i;
var slides = document.getElementsByClassName(“Slide”);
var dots = document.getElementsByClassName(“Navdot”);
if (n > slides.length) { slideIndex = 1; }
if (n (item.style.display = “none”));
Array.from(dots).forEach(
item => (item.className = item.className.replace(” selected”, “”))
);
slides[slideIndex – 1].style.display = “block”;
dots[slideIndex – 1].className += ” selected”;
}