Slovenian text summarization models

  Authors

Žagar, Aleš and Robnik-Šikonja, Marko

  Item identifier

http://hdl.handle.net/11356/1751

 Project URL

https://rsdo.slovenscina.eu/

 Demo URL

https://slovenscina.eu/povzemanje

 Date issued

2022-12-21

 Type

toolService

 Language(s)

Slovenian

 Description

A text summarisation task aims to convert a longer text into a shorter text while preserving the essential information of the source text. In general, there are two approaches to text summarization. The extractive approach simply rewrites the most important sentences or parts of the text, whereas the abstractive approach is more similar to human-made summaries. We release 5 models that cover extractive, abstractive, and hybrid types: Metamodel: a neural model based on the Doc2Vec document representation that suggests the best summariser. Graph-based model: unsupervised graph-based extractive approach that returns the N most relevant sentences. Headline model: a supervised abstractive approach (T5 architecture) that returns returns headline-like abstracts. Article model: a supervised abstract approach (T5 architecture) that returns short summaries. Hybrid-long model: unsupervised hybrid (graph-based and transformer model-based) approach that returns short summaries of long texts. Details and instructions to run and train the models are available at https://github.com/clarinsi/SloSummarizer. The web service with a demo is available at https://slovenscina.eu/povzemanje.

 Publisher

Faculty of Computer and Information Science, University of Ljubljana

 Acknowledgement

Ministry of Culture C3340-20-278001 "Development of Slovene in a Digital Environment"

 Subject(s)

text summarization T5 graph methods

 Collection(s)

CLARIN.SI data & tools

Show full item record