Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Muddu, Sri Raghava, Rangaraju, Rupasai, Siledar, Tejpalsingh, Nath, Swaroop, Bhattacharyya, Pushpak, Nath, Swaprava, Banerjee, Suman, Patil, Amey, Chelliah, Muthusamy, Singh, Sudhanshu Shekhar, Garera, Nikesh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916288893288448
author Muddu, Sri Raghava
Rangaraju, Rupasai
Siledar, Tejpalsingh
Nath, Swaroop
Bhattacharyya, Pushpak
Nath, Swaprava
Banerjee, Suman
Patil, Amey
Chelliah, Muthusamy
Singh, Sudhanshu Shekhar
Garera, Nikesh
author_facet Muddu, Sri Raghava
Rangaraju, Rupasai
Siledar, Tejpalsingh
Nath, Swaroop
Bhattacharyya, Pushpak
Nath, Swaprava
Banerjee, Suman
Patil, Amey
Chelliah, Muthusamy
Singh, Sudhanshu Shekhar
Garera, Nikesh
contents Opinion summarization in e-commerce encapsulates the collective views of numerous users about a product based on their reviews. Typically, a product on an e-commerce platform has thousands of reviews, each review comprising around 10-15 words. While Large Language Models (LLMs) have shown proficiency in summarization tasks, they struggle to handle such a large volume of reviews due to context limitations. To mitigate, we propose a scalable framework called Xl-OpSumm that generates summaries incrementally. However, the existing test set, AMASUM has only 560 reviews per product on average. Due to the lack of a test set with thousands of reviews, we created a new test set called Xl-Flipkart by gathering data from the Flipkart website and generating summaries using GPT-4. Through various automatic evaluations and extensive analysis, we evaluated the framework's efficiency on two datasets, AMASUM and Xl-Flipkart. Experimental results show that our framework, Xl-OpSumm powered by Llama-3-8B-8k, achieves an average ROUGE-1 F1 gain of 4.38% and a ROUGE-L F1 gain of 3.70% over the next best-performing model.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10886
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM
Muddu, Sri Raghava
Rangaraju, Rupasai
Siledar, Tejpalsingh
Nath, Swaroop
Bhattacharyya, Pushpak
Nath, Swaprava
Banerjee, Suman
Patil, Amey
Chelliah, Muthusamy
Singh, Sudhanshu Shekhar
Garera, Nikesh
Computation and Language
Machine Learning
Opinion summarization in e-commerce encapsulates the collective views of numerous users about a product based on their reviews. Typically, a product on an e-commerce platform has thousands of reviews, each review comprising around 10-15 words. While Large Language Models (LLMs) have shown proficiency in summarization tasks, they struggle to handle such a large volume of reviews due to context limitations. To mitigate, we propose a scalable framework called Xl-OpSumm that generates summaries incrementally. However, the existing test set, AMASUM has only 560 reviews per product on average. Due to the lack of a test set with thousands of reviews, we created a new test set called Xl-Flipkart by gathering data from the Flipkart website and generating summaries using GPT-4. Through various automatic evaluations and extensive analysis, we evaluated the framework's efficiency on two datasets, AMASUM and Xl-Flipkart. Experimental results show that our framework, Xl-OpSumm powered by Llama-3-8B-8k, achieves an average ROUGE-1 F1 gain of 4.38% and a ROUGE-L F1 gain of 3.70% over the next best-performing model.
title Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2406.10886