Bengali Quantum NLP : Sentiment Analysis of Bengali Statements on Social and Electronic Media using Quantum NLP and Bengali NLP
Abstract
Instead of being limited to single sentences, Quantum Natural Language Processing (QNLP) allows for the processing of larger texts. In addition to answering questions, we might also work on other projects like language creation or summarization. Finally, we can simply scale up the size of the meaning spaces and complexity of the jobs as hardware gets more powerful, which is obviously the ultimate goal. This project’s major objective is to introduce Quantum Natural Language Processing (QNLP) in a way that is clear to both NLP engineers and practitioners of quantum computing. The goal of QNLP, a relatively new use of quantum computing, is to express the meaning of phrases as vectors stored in quantum computers. The QNLP project’s objective is to specify the necessary procedures and mappings for tasks involving natural language processing on quantum computing systems. Given the immaturity of quantum technologies, it is crucial to permit the investigation of reliable techniques and fresh algorithms to take use of the computational space these platforms provide. An upcoming technique called Quantum Natural Language Processing (QNLP) has the potential to provide NLP tasks with a quantum advantage. We demonstrate the first use of QNLP for sentiment analysis in this study and demonstrate flawless test set accuracy for different simulation types as well as respectable accuracy for tests conducted on a noisy quantum device. To produce the re- sults, we use the "lambeq"- QNLP toolkit and t|ket > by Cambridge Quantum (Quantin- uum). In this project, we suggest a system that rates Newspaper headlines/articles, Social Media comments according to whether they are favorable or negative. Sentiment analysis and document clustering for English-Language Newspaper headlines have both been extensively studied. The Bengali language will receive the same treatment from us. For the project, News headlines from Bengali Newspapers, and comments from different Social Media have been used. To produce the results in Bengali Language, we have used the toolkit named "BNLP" (Natural Language Processing toolkit for Bengali Language). We are utilizing a web crawler to collect the required headlines in order to create a dataset for this project because there isn’t that much datasets of headlines for Bengali-Language Newspapers. Our goal is to develop a system that can accurately distinguish between positive and negative results from Bengali News headlines/ articles, and Social Media comments through the tests.
Understanding the Market: Present and Future of QNLP-
By implementing the lambeq and bnlp toolkit which we have used in this current study, this development will be incredibly fast-paced for our project. By using various text classifiers, frameworks in python languages we can use positive, negative including all diverse feedbacks and influences from various social medias and electronic medias written in bengali language. One could also vary the computational model, for example, one could use Measurement-Based Quantum Computation (MBQC as the ability to transfer quantum states in unit time to accelerate addition ) instead of circuits. Rather than being confined to single sentences, one could process larger text. We could work on other tasks besides question-answering, such as language generation, summarization, etc. Lastly, when hardware becomes more powerful we can simply scale up the size of the meaning spaces and complexity of the tasks which is clearly the overall objective.