An Abstractive Summarization Method Based on Global Gated Dual Encoder

Peng, Lü; Li, Qun; Lv, Le-Bin; Wang, Chong-Yu

doi:10.1007/978-3-030-60457-8_29

Cited by 4 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abstractive Document Summarization. Neural models for abstractive document summarization have been widely studied [25,26] since Rush et al [27] first employed the encoder and decoder framework. A series of improvements have been proposed based on different advanced techniques.…”

Section: Related Workmentioning

confidence: 99%

WHORU: Improving Abstractive Dialogue Summarization with Personal Pronoun Resolution

Zhou

2023

Electronics

View full text Add to dashboard Cite

With the abundance of conversations happening everywhere, dialogue summarization plays an increasingly important role in the real world. However, dialogues inevitably involve many personal pronouns, which hinder the performance of existing dialogue summarization models. This work proposes a framework named WHORU to inject external personal pronoun resolution (PPR) information into abstractive dialogue summarization models. A simple and effective PPR method for the dialogue domain is further proposed to reduce time and space consumption. Experiments demonstrated the superiority of the proposed methods. More importantly, WHORU achieves new SOTA results on SAMSum and AMI datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

WHORU: Improving Abstractive Dialogue Summarization with Personal Pronoun Resolution

Zhou

2023

Electronics

View full text Add to dashboard Cite

show abstract

A Data-to-Text Generation Model with Deduplicated Content Planning

Wang

Cao

et al. 2022

Big Data

View full text Add to dashboard Cite

Boundary-Aware Abstractive Summarization with Entity-Augmented Attention for Enhancing Faithfulness

Li,

Liu,

et al. 2024

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

With the successful application of deep learning, document summarization systems can produce more readable results. However, abstractive summarization still suffers from unfaithful outputs and factual errors, especially in named entities. Current approaches tend to employ external knowledge to improve model performance while neglecting the boundary information and the semantics of the entities. In this paper, we propose an entity-augmented method (EAM) to encourage the model to make full use of the entity boundary information and pay more attention to the critical entities. Experimental results on three Chinese and English summarization datasets show that our method outperforms several strong baselines and achieves state-of-the-art performance on the CLTS dataset. Our method can also improve the faithfulness of the summary and generalize well to different pre-trained language models. Moreover, we propose a method to evaluate the integrity of generated entities. Besides, we adapt the data augmentation method in the FactCC model according to the difference between Chinese and English in grammar and train a new evaluation model for factual consistency evaluation in Chinese summarization.

show abstract

An Abstractive Summarization Method Based on Global Gated Dual Encoder

Cited by 4 publications

References 12 publications

WHORU: Improving Abstractive Dialogue Summarization with Personal Pronoun Resolution

WHORU: Improving Abstractive Dialogue Summarization with Personal Pronoun Resolution

A Data-to-Text Generation Model with Deduplicated Content Planning

Boundary-Aware Abstractive Summarization with Entity-Augmented Attention for Enhancing Faithfulness

Contact Info

Product

Resources

About