MARS: Multilingual Aspect-centric Review Summarisation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915025843650560 |
|---|---|
| author | Mukku, Sandeep Sricharan Kanagarajan, Abinesh Aggarwal, Chetan Yenigalla, Promod |
| author_facet | Mukku, Sandeep Sricharan Kanagarajan, Abinesh Aggarwal, Chetan Yenigalla, Promod |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_09991 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MARS: Multilingual Aspect-centric Review Summarisation Mukku, Sandeep Sricharan Kanagarajan, Abinesh Aggarwal, Chetan Yenigalla, Promod Computation and Language 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. |
| title | MARS: Multilingual Aspect-centric Review Summarisation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.09991 |