Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEfficient Attentions for Long Document Summarization
الاهتمام الفعال لتلخيص وثيقة طويلة
384
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعرض تعقيدات الحسابية والذاكرة التربيعية للمحولات الكبيرة محدودة قابلية توسعها لتلخيص وثيقة طويلة.في هذه الورقة، نقترح هيبوس، وهو اهتمام مفكف مفكف من التشفير مع خطوات وضعية من الدرجة الأولى بفعالية المعلومات البارزة من المصدر.ونحن كذلك إجراء دراسة منهجية للانتباه الذاتية الفعالة الحالية.جنبا إلى جنب مع HEPOS، نحن قادرون على معالجة المزيد من الرموز عشرة أضعاف من النماذج الحالية التي تستخدم الاهتزازات الكاملة.للتقييم، نقدم مجموعة بيانات جديدة، الحكومة، مع وثائق وملخصات أطول بكثير.تشير النتائج إلى أن نماذجنا تنتج درجات Rouge أعلى بكثير من المقارنات التنافسية، بما في ذلك النتائج الجديدة من أحدث النتائج على PubMed.يوضح التقييم البشري أيضا أن نماذجنا تولد ملخصات أكثر إعلانية مع أخطاء أقل غير مانعة.
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with Hepos, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GovReport, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.
References used
https://aclanthology.org/
rate research
Read More
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 reiterated in a
set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.
This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle. Inspired by previous work which uses the Information Bottleneck principle for sentence compression, we exten
d it to document level summarization with two separate steps. In the first step, we use signal(s) as queries to retrieve the key content from the source document. Then, a pre-trained language model conducts further sentence search and edit to return the final extracted summaries. Importantly, our work can be flexibly extended to a multi-view framework by different signals. Automatic evaluation on three scientific document datasets verifies the effectiveness of the proposed framework. The further human evaluation suggests that the extracted summaries cover more content aspects than previous systems.
Multi-label document classification (MLDC) problems can be challenging, especially for long documents with a large label set and a long-tail distribution over labels. In this paper, we present an effective convolutional attention network for the MLDC
problem with a focus on medical code prediction from clinical documents. Our innovations are three-fold: (1) we utilize a deep convolution-based encoder with the squeeze-and-excitation networks and residual networks to aggregate the information across the document and learn meaningful document representations that cover different ranges of texts; (2) we explore multi-layer and sum-pooling attention to extract the most informative features from these multi-scale representations; (3) we combine binary cross entropy loss and focal loss to improve performance for rare labels. We focus our evaluation study on MIMIC-III, a widely used dataset in the medical domain. Our models outperform prior work on medical coding and achieve new state-of-the-art results on multiple metrics. We also demonstrate the language independent nature of our approach by applying it to two non-English datasets. Our model outperforms prior best model and a multilingual Transformer model by a substantial margin.
Neural-based summarization models suffer from the length limitation of text encoder. Long documents have to been truncated before they are sent to the model, which results in huge loss of summary-relevant contents. To address this issue, we propose t
he sliding selector network with dynamic memory for extractive summarization of long-form documents, which employs a sliding window to extract summary sentences segment by segment. Moreover, we adopt memory mechanism to preserve and update the history information dynamically, allowing the semantic flow across different windows. Experimental results on two large-scale datasets that consist of scientific papers demonstrate that our model substantially outperforms previous state-of-the-art models. Besides, we perform qualitative and quantitative investigations on how our model works and where the performance gain comes from.
To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. T
o mitigate these issues, this paper proposes HetFormer, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization. Specifically, we model different types of semantic nodes in raw text as a potential heterogeneous graph and directly learn heterogeneous relationships (edges) among nodes by Transformer. Extensive experiments on both single- and multi-document summarization tasks show that HetFormer achieves state-of-the-art performance in Rouge F1 while using less memory and fewer parameters.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
