Global Voices: Crossing Borders in Automatic News Summarization

TL;DR

This paper introduces Global Voices, a multilingual dataset for evaluating cross-lingual summarization, highlighting the impact of translation quality and limitations of ROUGE metrics in this context.

Contribution

It presents a new dataset for cross-lingual summarization, along with a high-quality evaluation method and analysis of translation effects and metric limitations.

Findings

Translation quality significantly affects summarization performance.

ROUGE metrics may not fully capture summary quality in cross-lingual tasks.

Crowdsourced evaluation improves summary quality assessment.

Abstract

We construct Global Voices, a multilingual dataset for evaluating cross-lingual summarization methods. We extract social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages. Especially, for the into-English summarization task, we crowd-source a high-quality evaluation dataset based on guidelines that emphasize accuracy, coverage, and understandability. To ensure the quality of this dataset, we collect human ratings to filter out bad summaries, and conduct a survey on humans, which shows that the remaining summaries are preferred over the social-network summaries. We study the effect of translation quality in cross-lingual summarization, comparing a translate-then-summarize approach with several baselines. Our results highlight the limitations of the ROUGE metric that are overlooked in monolingual summarization. Our dataset is available for download at https://forms.gle/gpkJDT6RJWHM1Ztz9 .