Multi-Target Cross-Lingual Summarization: a novel task and a language-neutral approach

TL;DR

This paper introduces a new multi-target cross-lingual summarization task focused on producing semantically coherent summaries in multiple languages, along with a re-ranking method and evaluation protocol to address semantic consistency.

Contribution

It defines a novel task of multi-target cross-lingual summarization and proposes a re-ranking approach and evaluation protocol to ensure semantic coherence across languages.

Findings

Proposed a re-ranking approach for multi-target summaries.

Developed a multi-criteria evaluation protocol for semantic coherence.

First step towards addressing semantic consistency in cross-lingual summarization.

Abstract

Cross-lingual summarization aims to bridge language barriers by summarizing documents in different languages. However, ensuring semantic coherence across languages is an overlooked challenge and can be critical in several contexts. To fill this gap, we introduce multi-target cross-lingual summarization as the task of summarizing a document into multiple target languages while ensuring that the produced summaries are semantically similar. We propose a principled re-ranking approach to this problem and a multi-criteria evaluation protocol to assess semantic coherence across target languages, marking a first step that will hopefully stimulate further research on this problem.