SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.03508 · 2019

Sentence Centrality Revisited for Unsupervised Summarization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Single document summarization has enjoyed renewed interests in recent years thanks to the popularity of neural network models and the availability of large-scale datasets. In this paper we develop an unsupervised approach arguing that it is unrealistic to expect large-scale and high-quality training data to be available or created for different types of summaries, domains, or languages. We revisit a popular graph-based ranking algorithm and modify how node (aka sentence) centrality is computed in two ways: (a)~we employ BERT, a state-of-the-art neural representation learning model to better capture sentential meaning and (b)~we build graphs with directed edges arguing that the contribution of any two nodes to their respective centrality is influenced by their relative position in a document. Experimental results on three news summarization datasets representative of different languages and writing styles show that our approach outperforms strong baselines by a wide margin.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1906.03508")
get_code_for_paper("1906.03508")
have("1906.03508")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1906.03508.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1906.03508.svg)](https://syntology.ai/paper/1906.03508)

Connect an agent — have() is free.