Extractive Summarization Tool for Legal and News Documents

Lawyers reviewing case files, journalists monitoring wire feeds, and students confronting dense readings all face the same problem: documents arrive faster than anyone can read them. Extractive summarization, selecting the most important sentences verbatim rather than generating new text, offers trustworthy compression because every sentence in the summary provably exists in the source. The intern builds a Python command-line tool implementing two complementary approaches. A frequency-based summarizer scores sentences by the importance of their words after NLTK-driven tokenization and stopword filtering, while a TextRank summarizer builds a sentence similarity graph with NetworkX and ranks sentences using the PageRank-style algorithm that treats each sentence as a node voting for its neighbors. Users feed in large text files and receive concise summaries at a chosen compression level, and a visualization option displays each sentence's importance score so users can see exactly why the algorithm kept what it kept. The project gives the intern a solid grounding in graph-based NLP and classical text scoring, practical experience designing a CLI that handles real documents gracefully, and a demonstrable tool relevant to legal, media, and education workflows where transparent, non-hallucinating summarization is a hard requirement.