English
Related papers

Related papers: AWESOME: GPU Memory-constrained Long Document Summ…

200 papers

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall…

Computation and Language · Computer Science 2018-05-29 Yen-Chun Chen , Mohit Bansal

Citation graphs can be helpful in generating high-quality summaries of scientific papers, where references of a scientific paper and their correlations can provide additional knowledge for contextualising its background and main…

Information Retrieval · Computer Science 2023-02-24 Zheheng Luo , Qianqian Xie , Sophia Ananiadou

Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language…

Machine Learning · Computer Science 2019-11-04 Rajeev Bhatt Ambati , Saptarashmi Bandyopadhyay , Prasenjit Mitra

Readers find text difficult to consume for many reasons. Summarization can address some of these difficulties, but introduce others, such as omitting, misrepresenting, or hallucinating information, which can be hard for a reader to notice.…

Human-Computer Interaction · Computer Science 2024-01-22 Ziwei Gu , Ian Arawjo , Kenneth Li , Jonathan K. Kummerfeld , Elena L. Glassman

Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone…

Computation and Language · Computer Science 2022-09-20 Xinya Du , Sha Li , Heng Ji

In this paper, we propose a novel neural single document extractive summarization model for long documents, incorporating both the global context of the whole document and the local context within the current topic. We evaluate the model on…

Computation and Language · Computer Science 2019-09-19 Wen Xiao , Giuseppe Carenini

Constructing accurate knowledge graphs from long texts and low-resource languages is challenging, as large language models (LLMs) experience degraded performance with longer input chunks. This problem is amplified in low-resource settings…

Computation and Language · Computer Science 2025-03-25 Divyansh Singh , Manuel Nunez Martinez , Bonnie J. Dorr , Sonja Schmer Galunder

Despite the prevalence of pretrained language models in natural language understanding tasks, understanding lengthy text such as document is still challenging due to the data sparseness problem. Inspired by that humans develop their ability…

Computation and Language · Computer Science 2023-12-04 Yueguan Wang , Naoki Yoshinaga

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…

Computation and Language · Computer Science 2021-06-01 Potsawee Manakul , Mark J. F. Gales

Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key…

Computation and Language · Computer Science 2021-02-17 Vidhisha Balachandran , Artidoro Pagnoni , Jay Yoon Lee , Dheeraj Rajagopal , Jaime Carbonell , Yulia Tsvetkov

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Computation and Language · Computer Science 2023-10-09 Fangyuan Xu , Weijia Shi , Eunsol Choi

A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently…

Computation and Language · Computer Science 2021-10-18 Logan Lebanoff , Bingqing Wang , Zhe Feng , Fei Liu

The availability of large-scale datasets has driven the development of neural models that create summaries from single documents, for generic purposes. When using a summarization system, users often have specific intents with various…

Computation and Language · Computer Science 2021-06-02 Yumo Xu , Mirella Lapata

Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 32K or 128K tokens), it is computationally expensive and can…

Computation and Language · Computer Science 2025-04-10 Hongjin Qian , Zheng Liu , Peitian Zhang , Kelong Mao , Defu Lian , Zhicheng Dou , Tiejun Huang

We introduce Mem2Mem, a memory-to-memory mechanism for hierarchical recurrent neural network based encoder decoder architectures and we explore its use for abstractive document summarization. Mem2Mem transfers "memories" via…

Computation and Language · Computer Science 2020-10-23 Jaehong Park , Jonathan Pilault , Christopher Pal

Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and…

Computation and Language · Computer Science 2017-06-14 Ed Collins , Isabelle Augenstein , Sebastian Riedel

This study develops a calibrated beam-based algorithm with awareness of the global attention distribution for neural abstractive summarization, aiming to improve the local optimality problem of the original beam search in a rigorous way.…

Computation and Language · Computer Science 2021-10-27 Ye Ma , Zixun Lan , Lu Zong , Kaizhu Huang

With the abundance of data and information in todays time, it is nearly impossible for man, or, even machine, to go through all of the data line by line. What one usually does is to try to skim through the lines and retain the absolutely…

Computation and Language · Computer Science 2024-02-09 Imaad Zaffar Khan , Amaan Aijaz Sheikh , Utkarsh Sinha

The objective of this work is to segment high-resolution images without overloading GPU memory usage or losing the fine details in the output segmentation map. The memory constraint means that we must either downsample the big image or…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Chuong Huynh , Anh Tran , Khoa Luu , Minh Hoai

Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…

Computation and Language · Computer Science 2022-03-16 Bo Pang , Erik Nijkamp , Wojciech Kryściński , Silvio Savarese , Yingbo Zhou , Caiming Xiong