A survey on dialogue summarization: Recent advances and new frontiers

X Feng, X Feng, B Qin - arxiv preprint arxiv:2107.03175, 2021 - arxiv.org
Dialogue summarization aims to condense the original dialogue into a shorter version
covering salient information, which is a crucial way to reduce dialogue data overload …

Dialoglm: Pre-trained model for long dialogue understanding and summarization

M Zhong, Y Liu, Y Xu, C Zhu, M Zeng - Proceedings of the AAAI …, 2022 - ojs.aaai.org
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, multi-person …

Taxonomy of abstractive dialogue summarization: scenarios, approaches, and future directions

Q Jia, Y Liu, S Ren, KQ Zhu - ACM Computing Surveys, 2023 - dl.acm.org
Abstractive dialogue summarization generates a concise and fluent summary covering the
salient information in a dialogue among two or more interlocutors. It has attracted significant …

Low-resource dialogue summarization with domain-agnostic multi-source pretraining

Y Zou, B Zhu, X Hu, T Gui, Q Zhang - arxiv preprint arxiv:2109.04080, 2021 - arxiv.org
With the rapid increase in the volume of dialogue data from daily life, there is a growing
demand for dialogue summarization. Unfortunately, training a large summarization model is …

Unsupervised dialogue topic segmentation with topic-aware contrastive learning

H Gao, R Wang, TE Lin, Y Wu, M Yang… - Proceedings of the 46th …, 2023 - dl.acm.org
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue
modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue …

CSDS: A fine-grained Chinese dataset for customer service dialogue summarization

H Lin, L Ma, J Zhu, L **ang, Y Zhou, J Zhang… - arxiv preprint arxiv …, 2021 - arxiv.org
Dialogue summarization has drawn much attention recently. Especially in the customer
service domain, agents could use dialogue summaries to help boost their works by quickly …

Todsum: Task-oriented dialogue summarization with state tracking

L Zhao, F Zheng, K He, W Zeng, Y Lei, H Jiang… - arxiv preprint arxiv …, 2021 - arxiv.org
Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues,
while summarization datasets for the broadly used task-oriented dialogue haven't been …

Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization

J **ao, Y Chen, Y Ou, H Yu, K Shu… - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Large language models (LLMs) like LLaMA, Baichuan and Bloom models show remarkable
ability with instruction fine-tuning in many natural language tasks. Nevertheless, for the …

Domain-oriented prefix-tuning: Towards efficient and generalizable fine-tuning for zero-shot dialogue summarization

L Zhao, F Zheng, W Zeng, K He, W Xu, H Jiang… - arxiv preprint arxiv …, 2022 - arxiv.org
The most advanced abstractive dialogue summarizers lack generalization ability on new
domains and the existing researches for domain adaptation in summarization generally rely …

Unsupervised dialogue topic segmentation with topic-aware utterance representation

H Gao, R Wang, TE Lin, Y Wu, M Yang… - arxiv preprint arxiv …, 2023 - arxiv.org
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue
modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue …