A Natural Language Process based LSTM Framework for Keyword Extraction

Abstract

The keyword extraction means document contains collection of terms by keyword extraction, which is an automated process. It is the process of identifying keyword from essential content of a given document. The functionality of many NLP systems are enhanced by keyword extraction, which is crucial problem in many Natural Language Processing (NLP) applications. In keyword extraction by using traditional methods use small amounts of data and produce inaccurate results. The main strategy used to analyze a large number of documents and extract relevant data is Keyword extraction. Especially young people, spend a lot of time searching the internet for relevant data for gaining and absorbing knowledge is time-consuming process of learning from a different sources. Therefore, Natural Language Process Based Long Short-Term Memory (LSTM) Framework for Keyword Extraction is introduced. In this analysis, the Neural Information Processing Systems (NIPS) dataset was used from Kaggle.The suggested system is primarily focused on scraping data from websites that provide summaries and keywords from the information extracted from multiple websites. It also provides ability for users to choose website or text of their choosing. The system is trained and evaluated using the NIPS Dataset, which extracts high-quality keywords from user-generated reviews. The LSTM model compares with existing methods. Experimental results show that the proposed model achieves higher precision, recall, and F1-score. The results demonstrate its effectiveness in capturing contextual and semantic relevance over baseline methods. Therefore, this proposed system helps to identify the main topic and summarize the content of a text. Hence, this system shows better results interms of accuracy, precision, recall and F1-score.