Multi-Target Cross-Lingual Summarization: a novel task and a language-neutral approach
Authors:
- Diogo PernesDPDiogo Pernes
- Afonso MendesAMAfonso Mendes
Preprint
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.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- A Survey on Cross-Lingual SummarizationTransactions of the Association for Computational Linguistics, 2022
- Multilingual Denoising Pre-training for Neural Machine TranslationTransactions of the Association for Computational Linguistics, 2020
- WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization2020
- COMET: A Neural Framework for MT Evaluation2020
- On Faithfulness and Factuality in Abstractive Summarization2020
- Unsupervised Cross-lingual Representation Learning at Scale2020
- Jointly Learning to Align and Summarize for Neural Cross-Lingual Summarization2020
- Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and BeyondTransactions of the Association for Computational Linguistics, 2019
- Quality Estimation for Machine Translation2018
- Generalized network design problemsEuropean Journal of Operational Research, 2003