Abstractive Summarization 2015


Notes:

There are two general approaches to automatic summarization, extraction and abstraction. Abstractive methods build an internal semantic representation and then use natural language generation techniques to create a summary that is closer to what a human might generate. Such a summary might contain words not explicitly present in the original.

  • Abstraction-based summarization
  • Abstractive summariSation
  • Automatic summarizer

Wikipedia:

References:

See also:

Abstractive Summarization 2013 | Abstractive Summarization 2014 | Machine Reading


Toward abstractive summarization using semantic representations F Liu, J Flanigan, S Thomson, N Sadeh, NA Smith – 2015 – repository.cmu.edu Abstract We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed to a set of AMR graphs, the graphs are transformed … Cited by 31 Related articles All 2 versions

A framework for multi-document abstractive summarization based on semantic role labelling A Khan, N Salim, YJ Kumar – Applied Soft Computing, 2015 – Elsevier Abstract We propose a framework for abstractive summarization of multi-documents, which aims to select contents of summary not from the source document sentences but from the semantic representation of the source documents. In this framework, contents of the … Cited by 17 Related articles All 4 versions

A neural attention model for abstractive sentence summarization AM Rush, S Chopra, J Weston – arXiv preprint arXiv:1509.00685, 2015 – arxiv.org Abstract: Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data- driven approach to abstractive sentence summarization. Our method utilizes a local … Cited by 105 Related articles All 14 versions

Abstractive meeting summarization as a Markov decision process G Murray – Canadian Conference on Artificial Intelligence, 2015 – Springer Abstract The task of abstractive summarization is formulated as a Markov Decision Process. Value Iteration is used to determine the optimal policy for natural language generation. While the approach is general, in this work we apply the system to the problem of … Cited by 3 Related articles All 6 versions

Multi-document abstractive summarization using ILP based multi-sentence compression S Banerjee, P Mitra, K Sugiyama – Proceedings of the 24th …, 2015 – comp.nus.edu.sg Abstract Abstractive summarization is an ideal form of summarization since it can synthesize information from multiple documents to create concise informative summaries. In this work, we aim at developing an abstractive summarizer. First, our proposed approach identifies … Cited by 9 Related articles All 10 versions

Abstractive multi-document summarization via phrase selection and merging L Bing, P Li, Y Liao, W Lam, W Guo… – arXiv preprint arXiv: …, 2015 – arxiv.org Abstract: We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases. Different from existing abstraction-based approaches, our … Cited by 23 Related articles All 10 versions

Abstractive multi-document summarization with semantic information extraction W Li – Proceedings of the 2015 Conference on Empirical …, 2015 – aclweb.org This paper proposes a novel approach to generate abstractive summary for multi- ple documents by extracting semantic in- formation from texts. The concept of Basic Semantic Unit (BSU) is defined to describe the semantics of an event or ac- tion. A semantic link network on BSUs is … Cited by 6 Related articles All 9 versions

Trends in extractive and abstractive techniques in text summarization N Bhatia, A Jaiswal – International Journal of Computer …, 2015 – search.proquest.com Abstract Text Summarization was proved to be an advantage over manually summarizing the large data. It condenses the salient features from the text by preserving the content and serves the meaningful summary. Classification can be done in two ways-extractive and … Cited by 1 Related articles All 5 versions

Abstractive meeting summarization using dependency graph fusion S Banerjee, P Mitra, K Sugiyama – Proceedings of the 24th International …, 2015 – dl.acm.org Abstract Automatic summarization techniques on meeting conversations developed so far have been primarily extractive, resulting in poor summaries. To improve this, we propose an approach to generate abstractive summaries by fusing important content from several … Cited by 2 Related articles All 11 versions

Conceptual Framework For Abstractive Text Summarization N Munot, SS Govilkar – academia.edu ABSTRACT As the volume of information available on the Internet increases, there is a growing need for tools helping users to find, filter and manage these resources. While more and more textual information is available online, effective retrieval is difficult without … Related articles

Genetic semantic graph approach for multi-document abstractive summarization A Khan, N Salim, YJ Kumar – Digital Information Processing …, 2015 – ieeexplore.ieee.org Abstract—The aim of automatic multi-document abstractive summarization is to create a compressed version of the source text and preserves the salient information. Existing graph based summarization methods treat sentence as bag of words, rely on content similarity … Cited by 2 Related articles

Machine Reading for Abstractive Summarization of Customer Reviews in the Touristic Domain E Hassan, D Buscaldi, A Gangemi – Septième Atelier Recherche d’ … – motive.cemagref.fr Abstract: Abstractive summarization is the task of producing a concise representation from a more complex text or a set of texts. This is a useful task especially in the summarization of customer reviews. In this paper we present an abstractive summarization method based … Related articles

Abstractive Multi-Document Text Summarization Using Automatic Text Summarizer Algorithm S Sridevi, S Priya – jrret.com Abstract-The number of web pages on the World Wide Web is increasing very rapidly. Consequently, a search engine like Google, AltaVista, and Bing etc. provides a long list of URLs to the end user. So, it becomes very difficult to review and analyze each web page … Related articles

Modelling on microblog posts clustering based on iteration feature selection and abstractive summarisation K Gao, B Zhang – International Journal of Modelling, …, 2015 – inderscienceonline.com With the coming of big data era, data mining and intelligent processing become more and more important, and modelling on novel big data processing is necessary. As micro-blog posts’ properties on short texts and the linguistic unreliable features, it is necessary to … Related articles

Swarm Semantic Hybrid Approach for Multi-document Abstractive Summarization A Khan, N Salim, AI Obasa – researchgate.net Abstract: Multi-document summarization aims to produce a compressed version of numerous online text documents and preserves the salient information. A particular challenge for multidocument summarization is that there is an inevitable overlap in the … Related articles

Task Knowledge in Abstractive Summarization PE Genest, G Lapalme – rali.iro.umontreal.ca Abstract This paper discusses the path towards asbtractive summarization and proposes a new knowledge-based methodology called KBABS as a step forward on this path. We propose to use both world knowledge, to identify useful content, and task knowledge, to … Related articles

Toward Abstractive Summarization Using Semantic Representations FLJFS Thomson, NSNA Smith – pdfs.semanticscholar.org Abstract We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed to a set of AMR graphs, the graphs are transformed … Related articles All 14 versions

An Optimized Semantic Technique for Multi-Document Abstractive Summarization A Khan, N Salim – Indian Journal of Science and Technology, 2015 – indjst.org Background/Objective: Multi-document summarization produces a concise summary from several online topically related documents. A major challenge in this domain is usually the information overlap in documents emanating from various sources. This paper introduces …

Tutorial on Abstractive Text Summarization A Siddharthan – nlgsummer.github.io Error correction for Multilingual Summarization Extractive approaches are limited in how they can address noisy input (output of machine transation) Replace sentences with similar ones from extraneous English Documents (Evans et al., 2004) Improves Readability Exact … Related articles

Abstractive microblogs summarization N Uvarova – 2015 – brage.bibsys.no Microblogging is a new electronic communication medium based on short status updates containing personal and instant information. Due to the popularity of microblogs, the volume of information is enormous and big portion of it is duplicative or irrelevant. The effective … Related articles All 2 versions

Abstractive Methods for Text Summarization A Siddharthan – homepages.abdn.ac.uk Error correction for Multilingual Summarization Extractive approaches are limited in how they can address noisy input (output of machine transation) Replace sentences with similar ones from extraneous English Documents (Evans et al., 2004) Improves Readability Exact … Related articles All 2 versions

Weakly Supervised Natural Language Processing Framework for Abstractive Multi-Document Summarization: Weakly Supervised Abstractive Multi-Document Summarization P Li, W Cai, H Huang – Proceedings of the 24th ACM International on …, 2015 – dl.acm.org Abstract In this paper, we propose a new weakly supervised abstractive news summarization framework using pattern based approaches. Our system first generates meaningful patterns from sentences. Then, in order to precisely cluster patterns, we … Related articles