<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "A Graph-Based Approach for the Summarization\r\nof Scientific Articles"^^ . "Automatic text summarization is one of the eminent applications in the field of\r\nNatural Language Processing. Text summarization is the process of generating\r\na gist from text documents. The task is to produce a summary which contains\r\nimportant, diverse and coherent information, i.e., a summary should be self-contained.\r\nThe approaches for text summarization are conventionally extractive.\r\nThe extractive approaches select a subset of sentences from an input document\r\nfor a summary. In this thesis, we introduce a novel graph-based extractive summarization\r\napproach.\r\nWith the progressive advancement of research in the various fields of science,\r\nthe summarization of scientific articles has become an essential requirement for\r\nresearchers. This is our prime motivation in selecting scientific articles as our\r\ndataset. This newly formed dataset contains scientific articles from the PLOS\r\nMedicine journal, which is a high impact journal in the field of biomedicine.\r\nThe summarization of scientific articles is a single-document summarization task.\r\nIt is a complex task due to various reasons, one of it being, the important information\r\nin the scientific article is scattered all over it and another reason being, scientific\r\narticles contain numerous redundant information. In our approach, we deal\r\nwith the three important factors of summarization: importance, non-redundancy\r\nand coherence. To deal with these factors, we use graphs as they solve data sparsity\r\nproblems and are computationally less complex.\r\nWe employ bipartite graphical representation for the summarization task, exclusively.\r\nWe represent input documents through a bipartite graph that consists of\r\nsentence nodes and entity nodes. This bipartite graph representation contains entity\r\ntransition information which is beneficial for selecting the relevant sentences\r\nfor a summary. We use a graph-based ranking algorithm to rank the sentences in\r\na document. The ranks are considered as relevance scores of the sentences which\r\nare further used in our approach.\r\nScientific articles contain reasonable amount of redundant information, for example,\r\nIntroduction and Methodology sections contain similar information regarding\r\nthe motivation and approach. In our approach, we ensure that the summary contains\r\nsentences which are non-redundant.\r\nThough the summary should contain important and non-redundant information of\r\nthe input document, its sentences should be connected to one another such that\r\nit becomes coherent, understandable and simple to read. If we do not ensure\r\nthat a summary is coherent, its sentences may not be properly connected. This\r\nleads to an obscure summary. Until now, only few summarization approaches\r\ntake care of coherence. In our approach, we take care of coherence in two different\r\nways: by using the graph measure and by using the structural information. We\r\nemploy outdegree as the graph measure and coherence patterns for the structural\r\ninformation, in our approach.\r\nWe use integer programming as an optimization technique, to select the best subset\r\nof sentences for a summary. The sentences are selected on the basis of relevance,\r\ndiversity and coherence measure. The computation of these measures is\r\ntightly integrated and taken care of simultaneously.\r\nWe use human judgements to evaluate coherence of summaries. We compare\r\nROUGE scores and human judgements of different systems on the PLOS Medicine\r\ndataset. Our approach performs considerably better than other systems on this\r\ndataset. Also, we apply our approach on the standard DUC 2002 dataset to compare\r\nthe results with the recent state-of-the-art systems. The results show that our\r\ngraph-based approach outperforms other systems on DUC 2002. In conclusion,\r\nour approach is robust, i.e., it works on both scientific and news articles. Our\r\napproach has the further advantage of being semi-supervised."^^ . "2020" . . . . . . . "Daraksha"^^ . "Parveen"^^ . "Daraksha Parveen"^^ . . . . . . "A Graph-Based Approach for the Summarization\r\nof Scientific Articles (PDF)"^^ . . . "Daraksha_Thesis.pdf"^^ . . . "A Graph-Based Approach for the Summarization\r\nof Scientific Articles (Other)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #27924 \n\nA Graph-Based Approach for the Summarization \nof Scientific Articles\n\n" . "text/html" . . . "400 Sprachwissenschaft"@de . "400 Linguistics"@en . .