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

@inproceedings{Fabbri2021ConvoSummCS,
  title={ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining},
  author={Alexander R. Fabbri and Faiaz Rahman and Imad Rizvi and Borui Wang and Haoran Li and Yashar Mehdad and Dragomir Radev},
  booktitle={ACL/IJCNLP},
  year={2021}
}
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… Expand
2 Citations

Figures and Tables from this paper

DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
  • Ming Zhong, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng
  • Computer Science
  • ArXiv
  • 2021
Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multiperson interactions in theExpand
A Survey on Dialogue Summarization: Recent Advances and New Frontiers
  • Xiachong Feng, Xiaocheng Feng, Bing Qin
  • Computer Science
  • ArXiv
  • 2021
TLDR
This first survey of dialogue summarization can provide the community with a quick access and a general picture to this task and motivate future researches. Expand

References

SHOWING 1-10 OF 80 REFERENCES
CQASUMM: Building References for Community Question Answering Summarization Corpora
TLDR
OdinioSumm is introduced, a new MDS which outperforms the best baseline by 4.6% w.r.t ROUGE-1 score and is compared to the popular MDS techniques and evaluated their performance on the CQA corpora. Expand
Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization
TLDR
This work proposes a multi-view sequence-to-sequence model by first extracting conversational structures of unstructured daily chats from different views to represent conversations and then utilizing amulti-view decoder to incorporate differentViews to generate dialogue summaries. Expand
Abstractive Dialog Summarization with Semantic Scaffolds
TLDR
This work proposes Scaffold Pointer Network (SPNet), an abstractive dialog summarization dataset based on MultiWOZ that outperforms state-of-the-art abstractive summarization methods on all the automatic and human evaluation metrics. Expand
Dialogue Discourse-Aware Graph Convolutional Networks for Abstractive Meeting Summarization
TLDR
A Dialogue Discourse-Aware Graph Convolutional Networks (DDA-GCN) for meeting summarization is developed by utilizing dialogue discourse, which is a dialogue-specific structure that can provide pre-defined semantic relationships between each utterance. Expand
Topic-Aware Pointer-Generator Networks for Summarizing Spoken Conversations
TLDR
This work proposes a topic-aware architecture to exploit the inherent hierarchical structure in conversations to further adapt the pointer-generator model, which significantly outperforms competitive baselines, achieves more efficient learning outcomes, and attains more robust performance. Expand
Using Summarization to Discover Argument Facets in Online Idealogical Dialog
TLDR
It is hypothesize that the CENTRAL PROPOSITIONS are exactly those arguments that people find most salient, and use human summarization as a probe for discovering them. Expand
Unsupervised Opinion Summarization as Copycat-Review Generation
TLDR
A generative model for a review collection is defined which capitalizes on the intuition that when generating a new review given a set of other reviews of a product, the authors should be able to control the “amount of novelty” going into the new review or, equivalently, vary the extent to which it deviates from the input. Expand
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
TLDR
This work considers the setting where there are only documents with no summaries provided, and proposes an end-to-end, neural model architecture to perform unsupervised abstractive summarization, and shows that the generated summaries are highly abstractive, fluent, relevant, and representative of the average sentiment of the input reviews. Expand
The SENSEI Annotated Corpus: Human Summaries of Reader Comment Conversations in On-line News
TLDR
A method is described to support humans in authoring conversation overview summaries and a publicly available corpus is presented – the first of its kind – of news articles plus comment sets, each multiply annotated, according to the method, with conversation Overview summaries. Expand
Characterizing Online Discussion Using Coarse Discourse Sequences
TLDR
A categorization of coarse discourse acts designed to encompass general online discussion and allow for easy annotation by crowd workers is devised, and the broadening of discourse acts from simply question and answer to a richer set of categories can improve the recall performance of Q&A extraction. Expand
...
1
2
3
4
5
...