$μ$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huot, Fantine, Maynez, Joshua, Alberti, Chris, Amplayo, Reinald Kim, Agrawal, Priyanka, Fierro, Constanza, Narayan, Shashi, Lapata, Mirella
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916110623834112
author Huot, Fantine
Maynez, Joshua
Alberti, Chris
Amplayo, Reinald Kim
Agrawal, Priyanka
Fierro, Constanza
Narayan, Shashi
Lapata, Mirella
author_facet Huot, Fantine
Maynez, Joshua
Alberti, Chris
Amplayo, Reinald Kim
Agrawal, Priyanka
Fierro, Constanza
Narayan, Shashi
Lapata, Mirella
contents Cross-lingual summarization consists of generating a summary in one language given an input document in a different language, allowing for the dissemination of relevant content across speakers of other languages. The task is challenging mainly due to the paucity of cross-lingual datasets and the compounded difficulty of summarizing and translating. This work presents $μ$PLAN, an approach to cross-lingual summarization that uses an intermediate planning step as a cross-lingual bridge. We formulate the plan as a sequence of entities capturing the summary's content and the order in which it should be communicated. Importantly, our plans abstract from surface form: using a multilingual knowledge base, we align entities to their canonical designation across languages and generate the summary conditioned on this cross-lingual bridge and the input. Automatic and human evaluation on the XWikis dataset (across four language pairs) demonstrates that our planning objective achieves state-of-the-art performance in terms of informativeness and faithfulness. Moreover, $μ$PLAN models improve the zero-shot transfer to new cross-lingual language pairs compared to baselines without a planning component.
format Preprint
id arxiv_https___arxiv_org_abs_2305_14205
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle $μ$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge
Huot, Fantine
Maynez, Joshua
Alberti, Chris
Amplayo, Reinald Kim
Agrawal, Priyanka
Fierro, Constanza
Narayan, Shashi
Lapata, Mirella
Computation and Language
Cross-lingual summarization consists of generating a summary in one language given an input document in a different language, allowing for the dissemination of relevant content across speakers of other languages. The task is challenging mainly due to the paucity of cross-lingual datasets and the compounded difficulty of summarizing and translating. This work presents $μ$PLAN, an approach to cross-lingual summarization that uses an intermediate planning step as a cross-lingual bridge. We formulate the plan as a sequence of entities capturing the summary's content and the order in which it should be communicated. Importantly, our plans abstract from surface form: using a multilingual knowledge base, we align entities to their canonical designation across languages and generate the summary conditioned on this cross-lingual bridge and the input. Automatic and human evaluation on the XWikis dataset (across four language pairs) demonstrates that our planning objective achieves state-of-the-art performance in terms of informativeness and faithfulness. Moreover, $μ$PLAN models improve the zero-shot transfer to new cross-lingual language pairs compared to baselines without a planning component.
title $μ$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge
topic Computation and Language
url https://arxiv.org/abs/2305.14205