Graph based Multi-Document Summarization with Latent Topics
نویسندگان
چکیده
منابع مشابه
Graph-based models for multi-document summarization
University of Ljubljana Faculty of Computer and Information Science Ercan Canhasi Graph-based models for multi-document summarization is thesis is about automatic document summarization, with experimental results on general, query, update and comparative multi-document summarization (MDS). We describe prior work and our own improvements on some important aspects of a summarization system, incl...
متن کاملGraph-based Neural Multi-Document Summarization
We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use ...
متن کاملImproved Affinity Graph Based Multi-Document Summarization
This paper describes an affinity graph based approach to multi-document summarization. We incorporate a diffusion process to acquire semantic relationships between sentences, and then compute information richness of sentences by a graph rank algorithm on differentiated intra-document links and inter-document links between sentences. A greedy algorithm is employed to impose diversity penalty on ...
متن کاملTopic-based Multi-Document Summarization with Probabilistic Latent Semantic Analysis
We consider the problem of query-focused multidocument summarization, where a summary containing the information most relevant to a user’s information need is produced from a set of topic-related documents. We propose a new method based on probabilistic latent semantic analysis, which allows us to represent sentences and queries as probability distributions over latent topics. Our approach comb...
متن کاملMulti-document Summarization with Graph Metrics
In this paper we introduce two systems RSumm and CNSumm, which are multi-document summarizers based on the adaptation of the singledocument relationship map and complex network methods, which represent texts as graphs and select sentences to compose the summary by using different graph traversing strategies and complex networks measures.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
سال: 2013
ISSN: 1347-7986,1881-7203
DOI: 10.3156/jsoft.25.914