Extract Summaries Research Articles

Automatic summarization of long text of Chinese patents based on PatBertsum model

Aiming at the problems of traditional text abstract extraction algorithms for processing long text of Chinese patents and unsatisfactory results of long abstract generation, the PatBertSum algorithm is proposed, which enables the algorithm to process long (more than 1500 words) patent text with high efficiency and generate high-quality long (more than 200 words) text summaries. The method is based on the improved BertSum algorithm model, using the new CLTPDS patented text dataset, processing long texts by Head-Tail, transforming Chinese input representations, generating sentence vectors using a pre-trained model, and capturing internal text features and text structure features to extract summaries. Experimentally, this paper demonstrates that the method has improved the recall and F-value of ROUGE by more than 8 percentage points compared with existing methods.

VOICE ENBALED Q & A SYSTEM

— The aim of question answering is to respond to queries that are expressed in natural language (QA). Question answering systems offer automated ways to locate solutions to queries posed in natural language. One important development in information can be seen in the concept of question-answering systems particularly in its capacity to retrieve information resources in a natural way, retrieval technologies method through effective wordfor-word querying and retrieval of the appropriate responses. The development of machine learning algorithms like text summarizing, which can automatically shorten lengthier texts and extract summaries of individual sections of text without losing the meaning, is another result of advances in NLP. Text summary is a cutting-edge method of information processing in a time-constrained and efficiency-obsessed culture. It shortens the amount of time needed to read and makes finding, analyzing, and assimilation of relevant information simpler. In order to answer the questions that users have asked and to provide a concise overview of the same context, a novel method for extracting text from a picture and converting it into text files has been developed. In order to validate the proposed methodologies, a manual evaluation of the quality of the responses was also carried out.

The Use of Transformer Model in Opinion Summarisation

We live in an age of information, therefore collected data and documentation are practically treasure resources. All about a business and its development can be estimated with clarity via statistics. Any machine that could really analyse information to predict a projected outcome is known for being extremely vital for the business. It is critical for the system to provide accurate and useful knowledge of the products in order to conduct accurate assessment. Summarisation is a technique for obtaining a rundown from series of sentences in a study or observation that facilitates us with understanding the basic content of the knowledge expressed within. Simple and brief summaries of just a product will assist the system in performing prospective product research and development. In our paper, we use a deep learning framework that provides to extract clean, relevant, brief summaries from comprehensive customer feedback. Strategies of abstractive text summarisation is used. The method of extracting the primary keyword from a statement and using them in the summary is defined as extractive text summarisation. We utilise abstractive summarisation in this case, which evolves from sample information and provides the best feasible description. Utilising Transformer with Depth Scaling MultiHeaded Attention as well as GloVe word embedding with positional encoding, we illustrate an abstractive approach to extract summaries from the Amazon fine food reviews dataset. Transformer aids in the parallelisation of workloads in order to process data more quickly. We have used an Attention layer which boost the model's quality and enables it to become more effective. The BLUE rating is used to quantify the model's potency.

Recent Advances in Arabic Automatic Text Summarization

Recently, the volume of the Arabic texts and documents on the internet had increased rabidly and generated a rich and valuable content on the www. Several parties had contributed to this content, this includes researchers, companies, governmental agencies, educational institutions, etc. With this big content it became difficult to search and extract useful information using only mankind skills and search engines. This motivated researchers to propose automated methodologies to extract summaries or useful information from those documents. A lot of research has been proposed for the automatic extraction of summaries for the English language and other languages. Unfortunately, the research for the Arabic automatic text summarization is still humble and needs more attention. This study presents a critical review and analysis of recent studies in Arabic automatic text summarization. The review includes all recent studies used the different text summarization approaches which include statistical-based, graph-based, evolutionary-based, and machine learning-based approaches. The selection criteria of the literature are based on the venue of publication and year of publication; back to five years. All review papers in Arabic ATS are excluded from the review since the study considers the recent methodologies in Arabic ATS. As a conclusion of this research, we recommend researchers in Arabic text summarization to investigate the use of machine learning on abstractive approach for text summarization due to the lack of research in this area. Keywords: Automatic Text Summarization, The Arabic Language, Machine Learning, Natural Language Processing, Text Processing, Computational Linguistics.

Analysis of Competitor Intelligence in the Era of Big Data: An Integrated System Using Text Summarization Based on Global Optimization

Automatic text summarization can be applied to extract summaries from competitor intelligence (CI) corpora that organizations create by gathering textual data from the Internet. Such a representation of CI text is easier for managers to interpret and use for making decisions. This research investigates design of an integrated system for CI analysis which comprises clustering and automatic text summarization and evaluates quality of extractive summaries generated automatically by various text-summarization techniques based on global optimization. This research is conducted using experimentation and empirical analysis of results. A survey of practicing managers is also carried out to understand the effectiveness of automatically generated summaries from CI perspective. Firstly, it shows that global optimization-based techniques generate good quality extractive summaries for CI analysis from topical clusters created by the clustering step of the integrated system. Secondly, it shows the usefulness of the generated summaries by having them evaluated by practicing managers from CI perspective. Finally, the implication of this research from the point of view of theory and practice is discussed.

An abstractive Arabic text summarizer with user controlled granularity

Automated summaries help tackle the ever growing volume of information floating around. There are two broad categories: extract and abstract. In the former we retain the more important sentences more or less in their original structure, while the latter requires a fusion of multiple sentences and/or paraphrasing. This is a more challenging task than extract summaries. In this paper, we present a novel generic abstract summarizer for a single document in Arabic language. The system starts by segmenting the input text topic wise. Then, each textual segment is extractively summarized. Finally, we apply rule-based sentence reduction technique. The RST-based extractive summarizer is an enhanced version of the system in Azmi and Al-Thanyyan (2012). By controlling the size of the extract summary of each segment we can cap the size of the final abstractive summary. Both summarizers, the enhanced extractive and the abstractive, were evaluated. We tested our enhanced extractive summarizer on the same dataset in the aforementioned paper, using the measures recall, precision and Rouge. The results show noticeable improvement in the performance, specially the precision in shorter summaries. The abstractive summarizer was tested on a set of 150 documents, generating summaries of sizes 50%, 40%, 30% and 20% (of the original’s word count). The results were assessed by two human experts who graded them out of a maximum score of 5. The average score ranged between 4.53 and 1.92 for summaries at different granularities, with shorter summaries receiving the lower score. The experimental results are encouraging and demonstrate the effectiveness of our approach.

Addressing the Problem of Coherence in Automatic Text Summarization: A Latent Semantic Analysis Approach

This article is concerned with addressing the problem of coherence in the automatic summarization of prose fiction texts. Despite the increasing advances within the summarization theory, applications and industry, many problems are still unresolved in relations to the applications of the summarization theory to literature. This can be in part attributed to the peculiar nature of literary texts where standard or typical summarization processes are not amenable for literature. This study, therefore, tends to bridge the gap between literature and summarization theory by proposing a summarization system that is based on more semantic-based approaches for extracting more meaningful and coherent summaries. Given that lack of coherence within summaries has its negative implications on understanding original texts; it follows that more effective methods should be developed in relation to the extraction of coherent summaries. In order to do this, a hybrid of methods including statistical (TF-IDF) and semantic (Latent Semantic Analysis LSA) methods were used to derive the most distinctive features and extract summaries from 10 English novellas. For evaluation purposes, both intrinsic and extrinsic methods are used for determining the quality of the extracted summaries. Results indicate that the integration of LSA into features extraction methods achieves better summarization performance outcomes in terms of coherence properties within the extracted summaries.

CMiner: Opinion Extraction and Summarization for Chinese Microblogs

Sentiment analysis of microblog texts has drawn lots of attention in both the academic and industrial fields. However, most of the current work only focuses on polarity classification. In this paper, we present an opinion mining system for Chinese microblogs called CMiner. Instead of polarity classification, CMiner focuses on more complicated opinion mining tasks - opinion target extraction and opinion summarization. Novel algorithms are developed for the two tasks and integrated into the end-to-end system. CMiner can help to effectively understand the users' opinion towards different opinion targets in a microblog topic. Specially, we develop an unsupervised label propagation algorithm for opinion target extraction. The opinion targets of all messages in a topic are collectively extracted based on the assumption that similar messages may focus on similar opinion targets. In addition, we build an aspect-based opinion summarization framework for microblog topics. After getting the opinion targets of all the microblog messages in a topic, we cluster the opinion targets into several groups and extract representative targets and summaries for each group. A co-ranking algorithm is proposed to rank both the opinion targets and microblog sentences simultaneously. Experimental results on a benchmark dataset show the effectiveness of our system and the algorithms.

Measures of spatio-temporal accuracy for time series land cover data

Remote sensing is a useful tool for monitoring changes in land cover over time. The accuracy of such time-series analyses has hitherto only been assessed using confusion matrices. The matrix allows global measures of user, producer and overall accuracies to be generated, but lacks consideration of any spatial aspects of accuracy. It is well known that land cover errors are typically spatially auto-correlated and can have a distinct spatial distribution. As yet little work has considered the temporal dimension and investigated the persistence or errors in both geographic and temporal dimensions. Spatio-temporal errors can have a profound impact on both change detection and on environmental monitoring and modelling activities using land cover data. This study investigated methods for describing the spatio-temporal characteristics of classification accuracy. Annual thematic maps were created using a random forest classification of MODIS data over the Jakarta metropolitan areas for the period of 2001–2013. A logistic geographically weighted model was used to estimate annual spatial measures of user, producer and overall accuracies. A principal component analysis was then used to extract summaries of the multi-temporal accuracy. The results showed how the spatial distribution of user and producer accuracy varied over space and time, and overall spatial variance was confirmed by the principal component analysis. The results indicated that areas of homogeneous land cover were mapped with relatively high accuracy and low variability, and areas of mixed land cover with the opposite characteristics. A multi-temporal spatial approach to accuracy is shown to provide more informative measures of accuracy, allowing map producers and users to evaluate time series thematic maps more comprehensively than a standard confusion matrix approach. The need to identify suitable properties for a temporal kernel are discussed.

Multi-Topic Multi-Document Summarizer

Current multi-document summarization systems can successfully extract summary sentences, however with many limitations including: low coverage, inaccurate extraction to important sentences, redundancy and poor coherence among the selected sentences. The present study introduces a new concept of centroid approach and reports new techniques for extracting summary sentences for multi-document. In both techniques keyphrases are used to weigh sentences and documents. The first summarization technique (Sen-Rich) prefers maximum richness sentences. While the second (Doc-Rich), prefers sentences from centroid document. To demonstrate the new summarization system application to extract summaries of Arabic documents we performed two experiments. First, we applied Rouge measure to compare the new techniques among systems presented at TAC2011. The results show that Sen-Rich outperformed all systems in ROUGE-S. Second, the system was applied to summarize multi-topic documents. Using human evaluators, the results show that Doc-Rich is the superior, where summary sentences characterized by extra coverage and more cohesion.

A System for Multicamera Task Recognition and Summarization for Structured Environments

In this paper, we propose a novel system for visual recognition and summarization of pick and place tasks that may be executed in settings such as an industrial assembly line. Our novel approach is based on the utilization of hidden Markov models for online task recognition as well as on the use of prior knowledge via a Hopfield-based optimization scheme. To facilitate offline analysis, we extract summaries of the captured content based on these features. We extract the motion energy using the norms of the Zernike moments, looking for local minima and maxima that indicate distinctive visual events and thus key-frames. The proposed scheme is not threshold-dependent, and, therefore, the number of extracted key-frames varies according to the complexity of motion energy variation. We validate our system by experimenting on two datasets.

Investigation of learners' perceptions for video summarization and recommendation

Recently, multimedia-based learning is widespread in educational settings. A number of studies investigate how to develop effective techniques to manage a huge volume of video sources, such as summarization and recommendation. However, few studies examine how these techniques affect learners' perceptions in multimedia learning systems. This article aims to examine learners' perceptions for summarization and recommendation, with an emphasis on the perspective of prior experience. In this study, we developed a multimedia content summarization and recommendation system, which can automatically extract summaries from raw video sources and recommend suitable video content to learners through emails. The results demonstrate that learners' prior experience and preferences for the presentation of document types affect their perceptions, including the enhancement of interests, the ease of information acquisition and the intention for the further use of the system. Finally, the findings are applied to develop a framework that can support for the design of multimedia learning systems.

1932 in Retrospect

Extract Summaries of the various annual reports prepared for the meeting scheduled for December 8, 1932, which was unavoidably postponed, are as follows: