priyansh4320/Abstractive-Text-Summarization-Enhancing-Sequence-to-Sequence-Models-Using-Word-Sense-Disambiguatio

This repository contains code and resources for abstractive text summarization (TS) using a novel framework that leverages knowledge-based word sense disambiguation (WSD) and semantic content generalization to enhance the performance of sequence-to-sequence (seq2seq) neural-based TS.

13
/ 100
Experimental

This project helps content creators, researchers, and analysts quickly get human-readable summaries from lengthy single-document texts. It takes in a full document and a taxonomy of concepts to produce a concise summary, making it easier to grasp key information without reading the entire original source. This is for anyone who needs to understand or convey the essence of long articles, reports, or research papers efficiently.

No commits in the last 6 months.

Use this if you need to automatically generate clear, concise summaries from single, complex documents, especially if those documents contain ambiguous or rare words.

Not ideal if you need to summarize multiple documents simultaneously or if your primary goal is to extract specific sentences rather than generate new summary text.

content-creation research-analysis information-extraction document-processing knowledge-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Jupyter Notebook

License

Last pushed

Sep 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/priyansh4320/Abstractive-Text-Summarization-Enhancing-Sequence-to-Sequence-Models-Using-Word-Sense-Disambiguatio"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.