An official website of the United States government
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 divideand- conquer strategies. The former reduces theoretical time complexity, but is still memoryheavy. 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, meeting transcripts, screenplays, 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.
more »
« less
This content will become publicly available on June 1, 2025
PELMS: Pre-training for Effective Low-Shot Multi-Document Summarization
We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pretraining strategy design, they struggle to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present PELMS, a pre-trained model that uses pre-training objectives based on semantic coherence heuristics and faithfulness constraints together with unlabeled multi-document inputs, to promote the generation of concise, fluent, and faithful summaries. To support the training of PELMS, we compile MultiPT, a multidocument pre-training corpus containing over 93 million documents to form more than 3 million unlabeled topic-centric document clusters, covering diverse genres such as product reviews, news, and general knowledge. We perform extensive evaluation of PELMS in lowshot settings on a wide range of MDS datasets. Our approach consistently outperforms competitive comparisons with respect to overall informativeness, abstractiveness, coherence, and faithfulness, and with minimal fine-tuning can match performance of language models at a much larger scale (e.g., GPT-4).
more »
« less
- Award ID(s):
- 2050130
- PAR ID:
- 10518832
- Publisher / Repository:
- Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Social media9s explosive growth has resulted in a massive influx of electronic documents influencing various facets of daily life. However, the enormous and complex nature of this content makes extracting valuable insights challenging. Long document summarization emerges as a pivotal technique in this context, serving to distill extensive texts into concise and comprehensible summaries. This paper presents a novel three-stage pipeline for effective long document summarization. The proposed approach combines unsupervised and supervised learning techniques, efficiently handling large document sets while requiring minimal computational resources. Our methodology introduces a unique process for forming semantic chunks through spectral dynamic segmentation, effectively reducing redundancy and repetitiveness in the summarization process. Contrary to previous methods, our approach aligns each semantic chunk with the entire summary paragraph, allowing the abstractive summarization model to process documents without truncation and enabling the summarization model to deduce missing information from other chunks. To enhance the summary generation, we utilize a sophisticated rewrite model based on Bidirectional and Auto- Regressive Transformers (BART), rearranging and reformulating summary constructs to improve their fluidity and coherence. Empirical studies conducted on the long documents from the Webis-TLDR-17 dataset demonstrate that our approach significantly enhances the efficiency of abstractive summarization transformers. The contributions of this paper thus offer significant advancements in the field of long document summarization, providing a novel and effective methodology for summarizing extensive texts in the context of social media.more » « less
-
Abstractive summarization models typically learn to capture the salient information from scratch implicitly.Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.However, extractive summaries as guidance could be over strict, leading to information loss or noisy signals.Furthermore, it cannot easily adapt to documents with various abstractiveness.As the number and allocation of salience content pieces varies, it is hard to find a fixed threshold deciding which content should be included in the guidance.In this paper, we propose a novel summarization approach with a flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as Guidance for Abstractive SummarizatiON).SEASON utilizes the allocation of salience expectation to guide abstractive summarization and adapts well to articles in different abstractiveness.Automatic and human evaluations on two benchmark datasets show that the proposed method is effective and reliable.Empirical results on more than one million news articles demonstrate a natural fifteen-fifty salience split for news article sentences, providing a useful insight for composing news articles.more » « less
-
Generating a high-quality explainable summary of a multi-review corpus can help people save time in reading the reviews. With natural language processing and text clustering, people can generate both abstractive and extractive summaries on a corpus containing up to 967 product reviews (Moody et al. 2022). However, the overall quality of the summaries needs further improvement. Noticing that online reviews in the corpus come from a diverse population, we take an approach of removing irrelevant human factors through pre-processing. Apply available pre-trained models together with reference based and reference free metrics, we filter out noise in each review automatically prior to summary generation. Our computational experiments evident that one may significantly improve the overall quality of an explainable summary from such a pre-processed corpus than from the original one. It is suggested of applying available high-quality pre-trained tools to filter noises rather than start from scratch. Although this work is on the specific multi-review corpus, the methods and conclusions should be helpful for generating summaries for other multi-review corpora.more » « less
-
Carlotta Demeniconi, Ian Davidson: (Ed.)Multi-document summarization, which summarizes a set of documents with a small number of phrases or sentences, provides a concise and critical essence of the documents. Existing multi-document summarization methods ignore the fact that there often exist many relevant documents that provide surrounding background knowledge, which can help generate a salient and discriminative summary for a given set of documents. In this paper, we propose a novel method, SUMDocS (Surrounding-aware Unsupervised Multi-Document Summarization), which incorporates rich surrounding (topically related) documents to help improve the quality of extractive summarization without human supervision. Speci fically, we propose a joint optimization algorithm to unify global novelty (i.e., category-level frequent and discriminative), local consistency (i.e., locally frequent, co-occurring), and local saliency (i.e., salient from its surroundings) such that the obtained summary captures the characteristics of the target documents. Extensive experiments on news and scientifi c domains demonstrate the superior performance of our method when the unlabeled surrounding corpus is utilized.more » « less
