ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining

06/01/2021
by   Alexander R. Fabbri, et al.
10

While online conversations can cover a vast amount of information in many different formats, abstractive text summarization has primarily focused on modeling solely news articles. This research gap is due, in part, to the lack of standardized datasets for summarizing online discussions. To address this gap, we design annotation protocols motivated by an issues–viewpoints–assertions framework to crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads. We benchmark state-of-the-art models on our datasets and analyze characteristics associated with the data. To create a comprehensive benchmark, we also evaluate these models on widely-used conversation summarization datasets to establish strong baselines in this domain. Furthermore, we incorporate argument mining through graph construction to directly model the issues, viewpoints, and assertions present in a conversation and filter noisy input, showing comparable or improved results according to automatic and human evaluations.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/07/2021

Summary Grounded Conversation Generation

Many conversation datasets have been constructed in the recent years usi...
10/12/2018

IndoSum: A New Benchmark Dataset for Indonesian Text Summarization

Automatic text summarization is generally considered as a challenging ta...
05/12/2021

What's The Latest? A Question-driven News Chatbot

This work describes an automatic news chatbot that draws content from a ...
01/27/2021

Pano: Engaging with News using Moral Framing towards Bridging Ideological Divides

Society is showing signs of strong ideological polarization. When pushed...
06/16/2021

Disentangling Online Chats with DAG-Structured LSTMs

Many modern messaging systems allow fast and synchronous textual communi...
08/08/2022

Abstractive Meeting Summarization: A Survey

Recent advances in deep learning, and especially the invention of encode...
11/14/2020

DebateSum: A large-scale argument mining and summarization dataset

Prior work in Argument Mining frequently alludes to its potential applic...

Code Repositories