Challenge: Existing pre-trained language models are difficult to apply to abstractive conversational summarization tasks.
Approach: They propose a thread-aware Transformer-based network that incorporates contextual dependency into the conversational summarization model.
Outcome: The proposed model can be applied to real conversations using a large-scale pretraining dataset.

Similar Papers

Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on text summarization focus on single-speaker docs, scientific publications and encyclopedia articles.
Approach: They propose a multi-view sequence-to-sequence model that extracts conversational structures from unstructured daily chats and incorporates different views to generate dialogue summaries.
Outcome: The proposed model outperforms state-of-the-art models via automatic evaluation and human judgment on a large-scale dialogue summarization corpus.
A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods of summarizing meetings require complex multi-step pipelines that are intractable.
Approach: They propose an abstractive summary network that adapts to meeting transcripts by hierarchical structure and role vectors.
Outcome: The proposed model outperforms existing methods in both metrics and human evaluation.
Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for meeting summary have limited the ability to deal with long-term dependency.
Approach: They propose a hierarchical transformer encoder-decoder network with multi-task pre-training to capture key sentences at word level and generate them at word-level.
Outcome: The proposed model is superior to the previous methods in meeting summary datasets AMI and ICSI.
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.
Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining (2020.coling-main)

Copied to clipboard

Challenge: Discourse parsing is an important upstream task within the area of Natural Language Processing (NLP) .
Approach: They propose a discourse parser that incorporates recent contextual language models to improve the performance of RST-based discourse parses.
Outcome: The proposed parser outperforms existing models on two key RST datasets and on large-scale "silver-standard" discourse treebank MEGA-DT.
Post-Training Dialogue Summarization using Pseudo-Paraphrasing (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to dialogue summarization use dialogue-specific features that require additional knowledge to recognize or make the models harder to tune.
Approach: They propose to post-train pretrained language models to rephrase from dialogue to narratives and fine-tune them as usual.
Outcome: The proposed approach outperforms existing models by summary quality and implementation costs.
A Theoretically Grounded Approach to Summarizing Conversation Dynamics for Forecasting the Derailment of Online Conversations (2026.acl-long)

Copied to clipboard

Challenge: Recent work on conversation derailment prediction relies on linguistic features rooted in linguistic and social theories.
Approach: They propose a system that predicts from the start of a conversation whether it will derail into toxic exchanges.
Outcome: The proposed system achieves 10% performance increase over baseline and 6.47% increase on benchmark dataset.
Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations (2021.findings-emnlp)

Copied to clipboard

Challenge: Using pretrained transformer models for automatically summarizing doctor-patient conversations presents challenges . limited training data, domain shift, long and noisy transcripts, and high target summary variability are challenges compared to human annotators.
Approach: They propose a method for fine-tuning pretrained transformer models for automatically summarizing doctor-patient conversations directly from transcripts.
Outcome: The proposed method surpasses the performance of an average human annotator and the quality of previous published work for the task.
TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing abstractive summarization models ignore abundant unlabeled corpora resources . TED outperforms all unsupervised abstractive baselines on NYT, CNN/DM and English Gigaword datasets .
Approach: They propose a transformer-based unsupervised text summarization system with pretraining on large-scale data.
Outcome: The proposed system outperforms baseline models on NYT, CNN/DM and English Gigaword datasets with various document styles.
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.

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