Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization

You, Jingyi; Li, Dongyuan; Kamigaito, Hidetaka; Funakoshi, Kotaro; Okumura, Manabu

doi:10.18653/v1/2022.naacl-main.301

Cited by 6 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This improved visual and text representation in medical report generation task. Furthermore, 3D shared subspace was also explored for representation improvement [19].…”

Section: Review Literaturementioning

confidence: 99%

CNX-B2: A Novel CNN-Transformer Approach For Chest X-Ray Medical Report Generation

Alqahtani,

Mohsan,

Alshamrani

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Medical imaging techniques are the most popular non-invasive methods to diagnose chest diseases. Chest X-ray scans are employed commonly to detect chronic obstructive pulmonary diseases and other respiratory diseases. Despite the significance of these diagnostic methods, the process of disease detection and the subsequent task of CXR report writing is tedious for radiologists. Therefore, Automated radiological report generation is a highly desirable task for radiologists. Previous studies were focused on the automated generation of medical reports to achieve greater quantitative scores rather than focusing on the quality of reports. Such approaches suffer from the problem of generating normal reports for CXR with diseases. Additionally, the absence of clear segregation between normal and abnormal samples in publicly available datasets its impossible to evaluate the performance of models in generating rare abnormal reports. To address these issues, we propose CNX-B2 which is a Convolutional Neural Network (CNN) combined with a Transformer approach to generate medical reports. The proposed encoder is designed to be both hybrid and efficient, capturing meaningful spatial features through inherent convolution biases. This enables the transformer-based decoder to robustly convert these features into coherent medical reports. Secondly, we also introduce a new radiological report dataset to evaluate model performances on abnormal reports separately. Our proposed model is further evaluated on the IU-Xray dataset, achieving competitive scores of 0.479 BLEU-1, 0.188 METEOR, and 0.586 CIDER.

show abstract

“…This improved visual and text representation in medical report generation task. Furthermore, 3D shared subspace was also explored for representation improvement [19].…”

Section: Review Literaturementioning

confidence: 99%

CNX-B2: A Novel CNN-Transformer Approach For Chest X-Ray Medical Report Generation

Alqahtani,

Mohsan,

Alshamrani

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Graph-Based Models Although graphs are commonly used to boost text summarization (Wu et al 2021b;You et al 2022;Song and King 2022), there are only a handful of models which have been proposed to use graphs to encode the documents in abstractive MDS (Li et al 2020;Jin, Wang, and Wan 2020;Li and Zhuge 2021;Cui and Hu 2021). Most of these models only leverage homogeneous graphs as they do not consider different edge types of graphs.…”

Section: Related Workmentioning

confidence: 99%

Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization

Lau

2023

AAAI

View full text Add to dashboard Cite

Multi-document summarization (MDS) aims to generate a summary for a number of related documents. We propose HGSum — an MDS model that extends an encoder-decoder architecture to incorporate a heterogeneous graph to represent different semantic units (e.g., words and sentences) of the documents. This contrasts with existing MDS models which do not consider different edge types of graphs and as such do not capture the diversity of relationships in the documents. To preserve only key information and relationships of the documents in the heterogeneous graph, HGSum uses graph pooling to compress the input graph. And to guide HGSum to learn the compression, we introduce an additional objective that maximizes the similarity between the compressed graph and the graph constructed from the ground-truth summary during training. HGSum is trained end-to-end with the graph similarity and standard cross-entropy objectives. Experimental results over Multi-News, WCEP-100, and Arxiv show that HGSum outperforms state-of-the-art MDS models. The code for our model and experiments is available at: https://github.com/oaimli/HGSum.

show abstract

“…The authors would like to gratefully acknowledge the reviewers for their time and valuable comments. This paper is an extended version of the paper (You et al 2022) accepted for publication at the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022). This extended version contains the following changes:…”

Section: Acknowledgementmentioning

confidence: 99%

Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization

You

Kamigaito

et al. 2023

Journal of Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Timeline summarization (TLS) is defined as a task for summarizing events in chronological order, which gives readers a comprehensive understanding of an evolutionary story. Previous studies on the timeline summarization (TLS) task ignored the information interaction between sentences and dates, and adopted pre-defined unlearnable representations for them, which significantly degrade the performance. They also considered date selection and event detection as two independent tasks, which makes it impossible to integrate their advantages and obtain a globally optimal summary. In this paper, we present a joint learning-based heterogeneous graph attention network for TLS (HeterTls), in which date selection and event detection are combined into a unified framework to improve the extraction accuracy and remove redundant sentences simultaneously. Our heterogeneous graph involves multiple types of nodes, the representations of which are iteratively learned across the heterogeneous graph attention layer. We evaluated our model on four datasets, and found that it significantly outperformed the current state-of-the-art baselines with regard to ROUGE scores and date selection metrics.

show abstract

Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization

Cited by 6 publications

References 22 publications

CNX-B2: A Novel CNN-Transformer Approach For Chest X-Ray Medical Report Generation

CNX-B2: A Novel CNN-Transformer Approach For Chest X-Ray Medical Report Generation

Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization

Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization

Contact Info

Product

Resources

About