Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207446,
        author = {Gitanjali Bhausaheb Adhane and Dr. Dipa Dattatray Dharmadhikari and Mrunal Mule},
        title = {Sentence Compression Using Natural Language Processing Technique},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {837-843},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207446},
        abstract = {Using extractive text summarization, we attempt sentence compression in this study. As a result, we are able to train a deep learning model to complete the job by rewriting it as a multi-label deletion-based issue. We can create summaries that are mainly grammatically sound and useful with fewer training examples and yet earn F1-Scores that are comparable to those from previous exams. Similar outcomes were obtained using a (Proof of Concept) POC of the model on a confidential dataset held by the author's employer. We describe a unique unsupervised sentence compression approach that uses a Stanford Typed Dependencies to extract information items and an NLP sentence compression engine to produce compressed phrases. An automated examination demonstrates that our strategy yields superior outcomes. A new compression technique tests grammaticality without a language model and compresses dependency trees. It's unsupervised, translatable, and considers syntax and word significance. The dependency-based approach is a good alternative to language model-based compression, enhancing system performance.},
        keywords = {Sentence Compression, Stanford, Natural Language Processing},
        month = {August},
        }