SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Parnell, Jacob, Unanue, Inigo Jauregi, Piccardi, Massimo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911804488155136
author Parnell, Jacob
Unanue, Inigo Jauregi
Piccardi, Massimo
author_facet Parnell, Jacob
Unanue, Inigo Jauregi
Piccardi, Massimo
contents Cross-lingual summarization (XLS) generates summaries in a language different from that of the input documents (e.g., English to Spanish), allowing speakers of the target language to gain a concise view of their content. In the present day, the predominant approach to this task is to take a performing, pretrained multilingual language model (LM) and fine-tune it for XLS on the language pairs of interest. However, the scarcity of fine-tuning samples makes this approach challenging in some cases. For this reason, in this paper we propose revisiting the summarize-and-translate pipeline, where the summarization and translation tasks are performed in a sequence. This approach allows reusing the many, publicly-available resources for monolingual summarization and translation, obtaining a very competitive zero-shot performance. In addition, the proposed pipeline is completely differentiable end-to-end, allowing it to take advantage of few-shot fine-tuning, where available. Experiments over two contemporary and widely adopted XLS datasets (CrossSum and WikiLingua) have shown the remarkable zero-shot performance of the proposed approach, and also its strong few-shot performance compared to an equivalent multilingual LM baseline, that the proposed approach has been able to outperform in many languages with only 10% of the fine-tuning samples.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13240
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization
Parnell, Jacob
Unanue, Inigo Jauregi
Piccardi, Massimo
Computation and Language
Cross-lingual summarization (XLS) generates summaries in a language different from that of the input documents (e.g., English to Spanish), allowing speakers of the target language to gain a concise view of their content. In the present day, the predominant approach to this task is to take a performing, pretrained multilingual language model (LM) and fine-tune it for XLS on the language pairs of interest. However, the scarcity of fine-tuning samples makes this approach challenging in some cases. For this reason, in this paper we propose revisiting the summarize-and-translate pipeline, where the summarization and translation tasks are performed in a sequence. This approach allows reusing the many, publicly-available resources for monolingual summarization and translation, obtaining a very competitive zero-shot performance. In addition, the proposed pipeline is completely differentiable end-to-end, allowing it to take advantage of few-shot fine-tuning, where available. Experiments over two contemporary and widely adopted XLS datasets (CrossSum and WikiLingua) have shown the remarkable zero-shot performance of the proposed approach, and also its strong few-shot performance compared to an equivalent multilingual LM baseline, that the proposed approach has been able to outperform in many languages with only 10% of the fine-tuning samples.
title SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization
topic Computation and Language
url https://arxiv.org/abs/2403.13240