最后,对上述提到的模型方法进行汇总成表格如下:7. 参考文献[1] An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics[2] Longformer: The Long-Document Transformer[3] Big Bird: Transformers for Longer Sequences[4] LongT5: Efficient Text-To-Text Transformer for Long Sequences[5] Investigating Efficiently Extending Transformers for Long Input Summarization[6] Efficient Attentions for Long Document Summarization[7] Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems[8] Multi Graph Neural Network for Extractive Long Document Summarization[9] HeterGraphLongSum: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization[10] Toward Unifying Text Segmentation and Long Document Summarization[11] Hierarchical Learning for Generation with Long Source Sequences.[12] Long Document Summarization with Top-down and Bottom-up Inference[13] Discourse-Aware Unsupervised Summarization of Long Scientific Documents[14] HEGEL: Hypergraph Transformer for Long Document Summarization[15] Leveraging Locality in Abstractive Text Summarization[16] A Divide-and-Conquer Approach to the Summarization of Long Documents[17] HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information[18] HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization[19] A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents[20] On Extractive and Abstractive Neural Document Summarization with Transformer Language Models[21] Long-Span Summarization via Local Attention and Content Selection[22] SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization[23] Sliding Selector Network with Dynamic Memory for Extractive Summarization of Long Documents[24] SUMMN : A Multi-Stage Summarization Framework for Long Input Dialogues and Documents[25] Leveraging Locality in Abstractive Text Summarization[26] Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks[27] GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization[28] Informative and Controllable Opinion Summarization[29] Summaformers @ LaySumm 20, LongSumm 20