MARS: Multilingual Aspect-centric Review Summarisation

TL;DR

This paper introduces MARS, a novel multilingual review summarization framework that extracts and summarizes customer feedback across languages, significantly improving efficiency and accuracy over existing methods.

Contribution

MARS presents a domain-agnostic, aspect-centric approach for multilingual review summarization using an extract-then-summarize paradigm, advancing the state-of-the-art.

Findings

Substantial improvements over abstractive baselines.

Enhanced efficiency for real-time systems.

Effective across multiple languages and domains.

Abstract

Summarizing customer feedback to provide actionable insights for products/services at scale is an important problem for businesses across industries. Lately, the review volumes are increasing across regions and languages, therefore the challenge of aggregating and understanding customer sentiment across multiple languages becomes increasingly vital. In this paper, we propose a novel framework involving a two-step paradigm \textit{Extract-then-Summarise}, namely MARS to revolutionise traditions and address the domain agnostic aspect-level multilingual review summarisation. Extensive automatic and human evaluation shows that our approach brings substantial improvements over abstractive baselines and efficiency to real-time systems.