OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Scientific Paper Summarisation

Scientific Paper Summarisation is a Python research project that uses supervised learning to extract summaries from scientific papers, with code for paper parsing, training-data preparation, model training, summary generation and evaluation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Scientific Paper Summarisation — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to study or work with a code-based supervised extractive summarisation workflow for scientific papers, particularly as part of literature-review research.

Who it is for

  • Researchers exploring extractive summarisation for scientific literature.
  • Developers who want to inspect or work with a paper-processing and model-training codebase.

Documented uses

  • Download and parse scientific paper files into the project's expected format.
  • Prepare parsed papers as training data for supervised summarisation models.
  • Train model modules and use trained models to generate paper summaries.
  • Evaluate summaries using ROUGE-L.
Before you choose

Requirements & limits

  • The README specifies Python 2.7 and installation of dependencies from requirements.txt.
  • The dataset and trained Word2Vec model are not included.
  • The README says preprocessing may take a while and that paths should be checked.
  • An AbstractNetPreprocessor used by the summarisers is described as inefficient.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare papers and training data

Download and parse papers, then convert them into the project's training-data format.

Before you start

  • Python 2.7 virtual environment
  • Requirements installed from requirements.txt
  • Repository code and access to the dataset downloaded by its data-acquisition script

Steps

  1. Run DataDownloader/acquire_data.py to download and parse the paper files.

  2. Run DataTools/DataPreprocessing/cspubsumext_creator.py to create training data.

Expected outcome

Training data is written by default to Data/Training_Data/, including individual JSON files and an all_data.json list.

Guide limitations

  • The dataset is not uploaded with the repository.
  • Preprocessing can take substantial time depending on the machine and number of cores.
  • Check and adjust paths in acquire_data.py and DataTools/useful_functions.py as needed.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
EdCo95/scientific-paper-summarisation · Official homepage title · retained in its source language
How we review sourcesSuggest a correction