AWESOME: GPU Memory-constrained Long Document Summarization using Memory
Mechanism and Global Salient Content
- URL: http://arxiv.org/abs/2305.14806v2
- Date: Thu, 16 Nov 2023 11:47:05 GMT
- Title: AWESOME: GPU Memory-constrained Long Document Summarization using Memory
Mechanism and Global Salient Content
- Authors: Shuyang Cao and Lu Wang
- Abstract summary: Long document summarization systems are critical for domains with lengthy and jargonladen text.
AWESOME produces summaries with improved informativeness, faithfulness, and coherence than competitive baselines on longer documents.
- Score: 16.458279293804285
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Long document summarization systems are critical for domains with lengthy and
jargonladen text, yet they present significant challenges to researchers and
developers with limited computing resources. Existing solutions mainly focus on
efficient attentions or divide-and-conquer strategies. The former reduces
theoretical time complexity, but is still memory-heavy. The latter methods
sacrifice global context, leading to uninformative and incoherent summaries.
This work aims to leverage the memory-efficient nature of divide-and-conquer
methods while preserving global context. Concretely, our framework AWESOME uses
two novel mechanisms: (1) External memory mechanisms track previously encoded
document segments and their corresponding summaries, to enhance global document
understanding and summary coherence. (2) Global salient content is further
identified beforehand to augment each document segment to support its
summarization. Extensive experiments on diverse genres of text, including
government reports, transcripts, scientific papers, and novels, show that
AWESOME produces summaries with improved informativeness, faithfulness, and
coherence than competitive baselines on longer documents, while having a
smaller GPU memory footprint.
Related papers
- Graph Neural Network and NER-Based Text Summarization [1.5850926890180461]
This project introduces an innovative approach to text summarization, leveraging the capabilities of Graph Neural Networks (GNNs) and Named Entity Recognition (NER) systems.
Our method aims to enhance the efficiency of summarization and also tries to ensures a high degree relevance in the condensed content.
arXiv Detail & Related papers (2024-02-05T03:00:44Z) - Enhancing Large Language Model with Self-Controlled Memory Framework [56.38025154501917]
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
We propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information.
arXiv Detail & Related papers (2023-04-26T07:25:31Z) - Document-Level Abstractive Summarization [0.0]
We study how efficient Transformer techniques can be used to improve the automatic summarization of very long texts.
We propose a novel retrieval-enhanced approach which reduces the cost of generating a summary of the entire document by processing smaller chunks.
arXiv Detail & Related papers (2022-12-06T14:39:09Z) - Dynamic Global Memory for Document-level Argument Extraction [63.314514124716936]
We introduce a new global neural generation-based framework for document-level event argument extraction.
We use a document memory store to record the contextual event information and leverage it to implicitly and explicitly help with decoding of arguments for later events.
Empirical results show that our framework outperforms prior methods substantially.
arXiv Detail & Related papers (2022-09-18T23:45:25Z) - Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
We propose a principled inference framework to improve summarization models on two aspects.
Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency.
We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
arXiv Detail & Related papers (2022-03-15T01:24:51Z) - Unsupervised Summarization with Customized Granularities [76.26899748972423]
We propose the first unsupervised multi-granularity summarization framework, GranuSum.
By inputting different numbers of events, GranuSum is capable of producing multi-granular summaries in an unsupervised manner.
arXiv Detail & Related papers (2022-01-29T05:56:35Z) - Bringing Structure into Summaries: a Faceted Summarization Dataset for
Long Scientific Documents [30.09742243490895]
FacetSum is a faceted summarization benchmark built on Emerald journal articles.
Analyses and empirical results on our dataset reveal the importance of bringing structure into summaries.
We believe FacetSum will spur further advances in summarization research and foster the development of NLP systems.
arXiv Detail & Related papers (2021-05-31T22:58:38Z) - Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical
Supervision from Extractive Summaries [46.183289748907804]
We propose SOE, a pipelined system that outlines, outlining and elaborating for long text generation.
SOE produces long texts with significantly better quality, along with faster convergence speed.
arXiv Detail & Related papers (2020-10-14T13:22:20Z) - Learning to Ignore: Long Document Coreference with Bounded Memory Neural
Networks [65.3963282551994]
We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time.
We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy.
arXiv Detail & Related papers (2020-10-06T15:16:31Z) - From Standard Summarization to New Tasks and Beyond: Summarization with
Manifold Information [77.89755281215079]
Text summarization is the research area aiming at creating a short and condensed version of the original document.
In real-world applications, most of the data is not in a plain text format.
This paper focuses on the survey of these new summarization tasks and approaches in the real-world application.
arXiv Detail & Related papers (2020-05-10T14:59:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.