Challenge: Abstractive text summarization has primarily focused on modeling news articles . lack of standardized datasets for summarizing online conversations is a major problem .
Approach: They propose to crowdsource four new datasets for summarizing online conversations . they incorporate argument mining through graph construction to directly model issues, viewpoints, and assertions present in a conversation.
Outcome: The proposed models are compared against widely-used conversation summarization datasets and show comparable or improved results.

Similar Papers

Abstractive Meeting Summarization: A Survey (2023.tacl-1)

Copied to clipboard

Challenge: Recent advances in deep learning have improved language generation systems, opening the door to improved forms of abstractive summarization.
Approach: They propose to use neural encoder-decoder architectures to generate abstractive meeting summarizations that are particularly well-suited for multi-party conversation.
Outcome: The proposed system could be used in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls.
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs (2021.naacl-main)

Copied to clipboard

Challenge: Abstractive conversation summarization has received much attention, but it suffers from insufficient, redundant, or incorrect content due to the unstructured and complex characteristics of human-human interactions.
Approach: They propose to model rich structures in conversations for more precise and accurate conversation summarization by incorporating discourse relations between utterances and action triples in utterrances and designing a multi-granularity decoder to generate summaries by combining all levels of information.
Outcome: The proposed models outperform state-of-the-art methods and generalize well in other domains in terms of automatic evaluations and human judgments.
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing work on abstractive dialogue summarizations has focused on news summarizing but there is no such comprehensive dataset.
Approach: They propose to use a chat-dialogues corpus with abstractive dialogue summaries to generate a short version of text that covers the main points succinctly.
Outcome: The proposed dataset achieves higher ROUGE scores than the model-generated summaries of news, compared with human evaluators' judgement.
Template-based Abstractive Microblog Opinion Summarization (2022.tacl-1)

Copied to clipboard

Challenge: Existing work on Twitter uses extractive summarization to filter through information, but this approach often includes incomplete or redundant information.
Approach: They propose to use Twitter data to generate 3100 gold-standard opinion summaries.
Outcome: The proposed method outperforms previous work on extractive summarization models and fine-tunes to improve performance.
Compositional Data Augmentation for Abstractive Conversation Summarization (2023.acl-long)

Copied to clipboard

Challenge: Abstractive conversation summarization systems rely on large-scale annotated summaries, but collecting and annotating these conversations can be time-consuming and labor-intensive.
Approach: They propose a method for generating diverse and high-quality pairs of conversations and summaries by extracting conversation structures and organizing meaningful conversation snippets.
Outcome: The proposed method outperforms baseline methods on SAMSum and DialogSum datasets and achieves a 10% increase in ROUGE scores with limited data.
ForumSum: A Multi-Speaker Conversation Summarization Dataset (2021.findings-emnlp)

Copied to clipboard

Challenge: Abstractive summarization quality has been improved but there is a lack of data for conversation summarizing applications.
Approach: They propose to build a conversation summarization dataset with human written summaries from internet forums.
Outcome: The proposed dataset can be easily expanded to improve conversation summarization applications.
ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining (2022.coling-1)

Copied to clipboard

Challenge: Existing abstractive summarization models do not take into account argumentative structure of legal documents, which poses a challenge towards effective abstractive summary.
Approach: They propose a technique that integrates argument role labeling into the summarization process by integrating argument role labels into the document.
Outcome: The proposed method improves over strong baselines with pretrained language models.
Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Abstractive conversation summarization models heavily rely on human-annotated summaries.
Approach: They propose a set of Conversational Data Augmentation methods for semi-supervised abstractive conversation summarization that use random swapping/deletion to perturb the discourse relations inside conversations and dialogue-acts-guided insertion to interrupt the development of conversations.
Outcome: The proposed methods over several state-of-the-art datasets show that they are more efficient than previous methods.
Summarization of Dialogues and Conversations At Scale (2023.eacl-tutorials)

Copied to clipboard

Challenge: Conversations are the natural communication format for people.
Approach: This tutorial will survey the cutting-edge methods for summarizing written and spoken conversation.
Outcome: This tutorial will examine the cutting-edge methods for summarizing written and spoken conversations, covering key sub-areas whose combination is needed for a successful solution.
EmailSum: Abstractive Email Thread Summarization (2021.acl-long)

Copied to clipboard

Challenge: Recent years have brought about interest in the task of summarizing conversation threads.
Approach: They develop an email thread summarization dataset that contains human-annotated short and long email threads over a wide variety of topics.
Outcome: The proposed dataset contains human-annotated short (30 words) and long (100 words) summaries of 2,549 email threads over a wide variety of topics.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations