Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTopic-Guided Abstractive Multi-Document Summarization
التلخيص التلقائي متعدد الوثائق الموجهة للموضوع
548
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقطة حرجة في تلخيص المستندات المتعددة (MDS) هي معرفة العلاقات بين مختلف الوثائق. في هذه الورقة، نقترح نموذجا جديدا للمغادرات الرواية، حيث نمثل مستندات متعددة كشركة بيانية غير متجانسة، حيث أخذت العقد الدلالية من التحبيبات المختلفة في الاعتبار، ثم قم بتطبيق إطار رسم بياني للتسلسل لتوليد ملخصات. علاوة على ذلك، فإننا نوظف نموذج موضوع عصبي لاستكشاف المواضيع الكامنة المشتركة التي يمكن أن تكون بمثابة وحدات دلالية عبر الوثيقة لتسجيل مستندات مختلفة وتوفير معلومات عالمية لتوجيه الجيل الموجز. نظرا لأن استخراج الموضوع يمكن أن ينظر إليه كنوع خاص من التلخيص الذي يلخص النصوص "نصوص" في شكل مجردة أكثر، أي توزيع موضوعي، نعتمد استراتيجية تعليمية متعددة المهام لتدريب المظهر والتلخيص المشترك، مما يسمح للترقية بعضهم البعض. توضح النتائج التجريبية على مجموعة بيانات الأخبار المتعددة أن نموذجنا يتفوق على نماذج MDS السابقة في كل من درجات Rouge والتقييم البشري، وفي الوقت نفسه يتعلم موضوعات عالية الجودة.
A critical point of multi-document summarization (MDS) is to learn the relations among various documents. In this paper, we propose a novel abstractive MDS model, in which we represent multiple documents as a heterogeneous graph, taking semantic nodes of different granularities into account, and then apply a graph-to-sequence framework to generate summaries. Moreover, we employ a neural topic model to jointly discover latent topics that can act as cross-document semantic units to bridge different documents and provide global information to guide the summary generation. Since topic extraction can be viewed as a special type of summarization that summarizes'' texts into a more abstract format, i.e., a topic distribution, we adopt a multi-task learning strategy to jointly train the topic and summarization module, allowing the promotion of each other. Experimental results on the Multi-News dataset demonstrate that our model outperforms previous state-of-the-art MDS models on both Rouge scores and human evaluation, meanwhile learns high-quality topics.
References used
https://aclanthology.org/
rate research
Read More
We present a method for generating comparative summaries that highlight similarities and contradictions in input documents. The key challenge in creating such summaries is the lack of large parallel training data required for training typical summari
zation systems. To this end, we introduce a hybrid generation approach inspired by traditional concept-to-text systems. To enable accurate comparison between different sources, the model first learns to extract pertinent relations from input documents. The content planning component uses deterministic operators to aggregate these relations after identifying a subset for inclusion into a summary. The surface realization component lexicalizes this information using a text-infilling language model. By separately modeling content selection and realization, we can effectively train them with limited annotations. We implemented and tested the model in the domain of nutrition and health -- rife with inconsistencies. Compared to conventional methods, our framework leads to more faithful, relevant and aggregation-sensitive summarization -- while being equally fluent.
Recent research using pre-trained language models for multi-document summarization task lacks deep investigation of potential erroneous cases and their possible application on other languages. In this work, we apply a pre-trained language model (BART
) for multi-document summarization (MDS) task using both fine-tuning and without fine-tuning. We use two English datasets and one German dataset for this study. First, we reproduce the multi-document summaries for English language by following one of the recent studies. Next, we show the applicability of the model to German language by achieving state-of-the-art performance on German MDS. We perform an in-depth error analysis of the followed approach for both languages, which leads us to identifying most notable errors, from made-up facts and topic delimitation, and quantifying the amount of extractiveness.
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.
Allowing users to interact with multi-document summarizers is a promising direction towards improving and customizing summary results. Different ideas for interactive summarization have been proposed in previous work but these solutions are highly di
vergent and incomparable. In this paper, we develop an end-to-end evaluation framework for interactive summarization, focusing on expansion-based interaction, which considers the accumulating information along a user session. Our framework includes a procedure of collecting real user sessions, as well as evaluation measures relying on summarization standards, but adapted to reflect interaction. All of our solutions and resources are available publicly as a benchmark, allowing comparison of future developments in interactive summarization, and spurring progress in its methodological evaluation. We demonstrate the use of our framework by evaluating and comparing baseline implementations that we developed for this purpose, which will serve as part of our benchmark. Our extensive experimentation and analysis motivate the proposed evaluation framework design and support its viability.
Information overload has been one of the challenges regarding information from the Internet. It is not a matter of information access, instead, the focus had shifted towards the quality of the retrieved data. Particularly in the news domain, multiple
outlets report on the same news events but may differ in details. This work considers that different news outlets are more likely to differ in their writing styles and the choice of words, and proposes a method to extract sentences based on their key information by focusing on the shared synonyms in each sentence. Our method also attempts to reduce redundancy through hierarchical clustering and arrange selected sentences on the proposed orderBERT. The results show that the proposed unsupervised framework successfully improves the coverage, coherence, and, meanwhile, reduces the redundancy for a generated summary. Moreover, due to the process of obtaining the dataset, we also propose a data refinement method to alleviate the problems of undesirable texts, which result from the process of automatic scraping.
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
