Fig 5 - uploaded by Xiaoping Sun
Content may be subject to copyright.
Source publication
Contexts in source publication
Context 1
... extract top-k sentences as representative sentences of one paper and return them back to its parent node. All the sentences extracted from the input papers at current leaf node are returned to its parent node. At the parent nodes, sentences from sub-sections will be reordered according to the rank of sub-sections and the types of subsections. Fig. 5 shows the details of the procedure for making survey at a leaf node. Each paper will be ranked by d c (n, k, D). All papers are sorted by their rank scores. Then, top-k sentences are selected from the sorted papers (Line 8-11 in Fig.4) to compose the survey content at the leaf ...
Context 2
... ranking papers and sentences as shown in Fig. 4 and Fig. 5, we compute a distance of each sentence to the keyword path of current node, as the score of the sentence of the paper at a given node. Then, we compute the score of the paper based on those sentence scores. The paper score is used as the distance from the paper to the keyword path string and will be used to rank papers in dimension ...
Similar publications
Citations
... To make the generated results have a clear hierarchy, Hoang and Kan [13] additionally inputs an associated topic hierarchy tree that describes a target paper's topics to drive the creation of an extractive related work section. Sun and Zhuge [31] proposes a template-based framework for survey paper automatic generation. It allows users to compose a template tree that consists of two types of nodes, dimension node and topic node. ...
Multi-document scientific summarization can extract and organize important information from an abundant collection of papers, arousing widespread attention recently. However, existing efforts focus on producing lengthy overviews lacking a clear and logical hierarchy. To alleviate this problem, we present an atomic and challenging task named Hierarchical Catalogue Generation for Literature Review (HiCatGLR), which aims to generate a hierarchical catalogue for a review paper given various references. We carefully construct a novel English Hierarchical Catalogues of Literature Reviews Dataset (HiCaD) with 13.8k literature review catalogues and 120k reference papers, where we benchmark diverse experiments via the end-to-end and pipeline methods. To accurately assess the model performance, we design evaluation metrics for similarity to ground truth from semantics and structure. Besides, our extensive analyses verify the high quality of our dataset and the effectiveness of our evaluation metrics. Furthermore, we discuss potential directions for this task to motivate future research.
... One common approach is leveraging cita-tion sentences to pinpoint important aspects of the papers. For instance, [45,33] exploit a template-based framework and composes a template-tree. The latter crawls citation index databases such as PubMed and Semantic Scholar and analyses the citation graph. ...
The increasing use of AI methods in various applications has raised concerns about their explainability and transparency. Many solutions have been developed within the last few years to either explain the model itself or the decisions provided by the model. However, the number of contributions in the field of eXplainable AI (XAI) is increasing at such a high pace that it is almost impossible for a newcomer to identify key ideas, track the field’s evolution, or find promising new research directions.Typically, survey papers serve as a starting point, providing a feasible entry point into a research area. However, this is not trivial for some fields with exponential growth in the literature, such as XAI. For instance, we analyzed 23 surveys in the XAI domain published within the last three years and surprisingly found no common conceptualization among them. This makes XAI one of the most challenging research areas to enter. To address this problem, we propose a systematic approach that enables newcomers to identify the principal ideas and track their evolution. The proposed method includes automating the retrieval of relevant papers, extracting their semantic relationship, and creating a temporal graph of ideas by post-analysis of citation graphs.The main outcome of our method is Field’s Evolution Graph (FEG), which can be used to find the core idea of each approach in this field, see how a given concept has developed and evolved over time, observe how different notions interact with each other, and perceive how a new paradigm emerges through combining multiple ideas. As for demonstration, we show that FEG successfully identifies the field’s key articles, such as LIME or Grad-CAM, and maps out their evolution and relationships.KeywordsField’s evolutionXAIExplainable AI
... To make the generated results have a clear hierarchy, Hoang and Kan (2010) additionally inputs an associated topic hierarchy tree that describes a target paper's topics to drive the creation of an extractive related work section. Sun and Zhuge (2019) proposes a template-based framework for survey paper automatic generation. It allows users to compose a template tree that consists of two types of nodes, dimension node and topic node. ...
... Based on the article's body as an input [38] Introduction summarization Extracting salient sentences in the introduction [39] Citation summarization Generating related work section [40] Highlight statements Generating highlight statements of articles [41] Multi Article Summarization Summarizing multi scientific articles [42,43] Scientific Survey Generation Generating a survey of many papers on a specific problem or domain [44] Presentation slides Generation Automatically creating presentation slides of a specific article [45] Medical Reports Summarization ...
Automatic Text Summarization (ATS) is an important area in Natural Language Processing (NLP) with the goal of shortening a long text into a more compact version by conveying the most important points in a readable form. ATS applications continue to evolve and utilize effective approaches that are being evaluated and implemented by researchers. State-of-the-Art (SotA) technologies that demonstrate cutting-edge performance and accuracy in abstractive ATS are deep neural sequence-to-sequence models, Reinforcement Learning (RL) approaches, and Transfer Learning (TL) approaches, including Pre-Trained Language Models (PTLMs). The graph-based Transformer architecture and PTLMs have influenced tremendous advances in NLP applications. Additionally, the incorporation of recent mechanisms, such as the knowledge-enhanced mechanism, significantly enhanced the results. This study provides a comprehensive review of recent research advances in the area of abstractive text summarization for works spanning the past six years. Past and present problems are described, as well as their proposed solutions. In addition, abstractive ATS datasets and evaluation measurements are also highlighted. The paper concludes by comparing the best models and discussing future research directions.
