Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis

10/11/2020
by   Roy Bar-Haim, et al.
0

When summarizing a collection of views, arguments or opinions on some topic, it is often desirable not only to extract the most salient points, but also to quantify their prevalence. Work on multi-document summarization has traditionally focused on creating textual summaries, which lack this quantitative aspect. Recent work has proposed to summarize arguments by mapping them to a small set of expert-generated key points, where the salience of each key point corresponds to the number of its matching arguments. The current work advances key point analysis in two important respects: first, we develop a method for automatic extraction of key points, which enables fully automatic analysis, and is shown to achieve performance comparable to a human expert. Second, we demonstrate that the applicability of key point analysis goes well beyond argumentation data. Using models trained on publicly available argumentation datasets, we achieve promising results in two additional domains: municipal surveys and user reviews. An additional contribution is an in-depth evaluation of argument-to-key point matching models, where we substantially outperform previous results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/04/2020

From Arguments to Key Points: Towards Automatic Argument Summarization

Generating a concise summary from a large collection of arguments on a g...
research
06/12/2021

Every Bite Is an Experience: Key Point Analysis of Business Reviews

Previous work on review summarization focused on measuring the sentiment...
research
05/25/2023

Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive Summarisation

Argument summarisation is a promising but currently under-explored field...
research
11/28/2022

Arguments to Key Points Mapping with Prompt-based Learning

Handling and digesting a huge amount of information in an efficient mann...
research
10/03/2021

Project Debater APIs: Decomposing the AI Grand Challenge

Project Debater was revealed in 2019 as the first AI system that can deb...
research
09/03/2017

Using Summarization to Discover Argument Facets in Online Ideological Dialog

More and more of the information available on the web is dialogic, and a...
research
12/23/2022

From Judgement's Premises Towards Key Points

Key Point Analysis(KPA) is a relatively new task in NLP that combines su...

Please sign up or login with your details

Forgot password? Click here to reset