Summarization, is to reduce the size of the document while preserving the meaning, is one of the most researched areas among the Natural Language Processing (NLP) community. Summarization techniques, on the basis of whether the exact sentences are considered as they appear in the original text or new sentences are generated using natural language processing techniques, are categorized into extractive and abstractive techniques. Extractive summarization has been a very extensively researched topic and has reached to its maturity stage. Now the research has shifted towards the abstractive summarization. The complexities underlying with the natural language text makes abstractive summarization a difficult and a challenging task.  This paper presents a comprehensive review of the various works performed in abstractive summarization field. For this purpose, we have selected the recent papers on this topic from Elsevier, ACM, IEEE, Springer, ACL Anthology, Cornell University Library and Google Scholar. The papers are categorized according to the type of abstractive technique used. The paper lists down the various challenges and discusses the future direction for research in this field. Along with these, we have identified the advantages and disadvantages of various methods used for abstractive summarization. We have also listed down the various tools which have been used or developed by researchers for abstractive summarization. The paper also discusses the evaluation techniques being used for assessing the abstractive summaries.

Abstractive summarization: An overview of the state of the art

Numerous techniques have been developed in order to prevent attacks on web servers Anomaly detection techniques are based on models of normal user and application behavior, interpreting deviations from the established pattern as indications of malicious activity In this work, a systematic review of the use of anomaly detection techniques in the prevention and detection of web attacks is undertaken; in particular, we used the standardized method of a systematic review of literature in the field of computer science, proposed by Kitchenham This method is applied to a set of 88 papers extracted from a total of 8041 reviewed papers, which have been published in notable journals This paper discusses the process carried out in this systematic review, as well as the results and findings obtained to identify the current state of the art of web anomaly detection

Prevention and Fighting against Web Attacks through Anomaly Detection Technology. A Systematic Review

In today’s digital world, online journalism plays a vital role across various facets of humanity, starting from day-to-day lives, to the extent of deciding presidential elections. Moreover, with the growth in popularity of automation in every possible field known to humans, automated journalism is an important domain to research into. In this, there are many factors that come into play such as relative importance of news and human emotions, apart from just statistical data. To determine the impact that artificial intelligence can have on online journalism, an automatically generating information platform using AI has been developed. The objective is to generate a fully functional information platform that creates content and news articles automatically, which is achieved by analyzing internet trends, mining data related to the trends from other news sources, classifying the data, and categorizing and generating information to resemble those written by human journalists, both grammatically and linguistically. This is achieved with the help of machine learning and NLTK (Natural Language Toolkit) modules for Python which is used to process trends across social media platforms, especially Twitter.

Efficient daily news platform generation using natural language processing

Bandung regency is one of Indonesian city that majority of the people are farmers. Farmers need weather information to determine the planting season. Weather forecasting become an orientation in agriculture sector to determining the beginning of planting season, and also quality and quantity of their harvest. One of the factors that affecting the harvest is rainfall. In this research, we make a classification model using C4.5 algorithm for rainfall forecasting at Bandung regency. Then, the post-pruning method is used to optimize pruning on the model. We used a weather data from BMKG (Meteorological, Climatological, and Geophysical Agency) in 2005 to 2016 period. The result of average accuracy testing without pruning is 60% and using pruning is 93.33%.

Rainfall Forecasting in Bandung Regency Using C4.5 Algorithm

Huge data on the web come from discussion forums, which contain millions of threads. Discussion threads are a valuable source of knowledge for Internet users, as they have information about numerous topics. The discussion thread related to single topic comprises a huge number of reply posts, which makes it hard for the forum users to scan all the replies and determine the most relevant replies in the thread. At the same time, it is also hard for the forum users to manually summarize the bulk of reply posts in order to get the gist of discussion thread. Thus, automatically extracting the most relevant replies from discussion thread and combining them to form a summary are a challenging task. With this motivation behind, this study has proposed a sentence embedding based clustering approach for discussion thread summarization. The proposed approach works in the following fashion: At first, word2vec model is employed to represent reply sentences in the discussion thread through sentence embeddings/sentence vectors. Next, K-medoid clustering algorithm is applied to group semantically similar reply sentences in order to reduce the overlapping reply sentences. Finally, different quality text features are utilized to rank the reply sentences in different clusters, and then the high-ranked reply sentences are picked out from all clusters to form the thread summary. Two standard forum datasets are used to assess the effectiveness of the suggested approach. Empirical results confirm that the proposed sentence based clustering approach performed superior in comparison to other summarization methods in the context of mean precision, recall, and F-measure.

/pdf/sentence-embedding-based-semantic-clustering-approach-for-2c5ybacpjn.pdf

Sentence Embedding Based Semantic Clustering Approach for Discussion Thread Summarization

Text summarization is to generate a condensed version of the original document. The major issues for text summarization are eliminating redundant information, identifying important difference among documents, and recovering the informative content. This paper proposes a Semantic Graph Model which exploits the semantic information of sentence using FSGM. FSGM treats sentences as vertexes while the semantic relationship as the edges. It uses FrameNet and word embedding to calculate the similarity of sentences. This method assigns weight to both sentence nodes and edges. After all, it proposes an improved method to rank these sentences, considering both internal and external information. The experimental results show that the applicability of the model to summarize text is feasible and effective.

https://downloads.hindawi.com/journals/sp/2016/5130603.pdf

Text Summarization Using FrameNet-Based Semantic Graph Model

Text summarization is to generate a condensed version of the original document. The major issues for text summarization are eliminating redundant information, identifying important difference among documents and covering the informative content. In this paper, we propose a Sentence-Level Semantic Graph Model (SLSGM) which exploits the semantic information of sentence. SLSGM considers sentences as vertexes while the semantic relationship between sentences as the edges. We calculate the relevance values between sentences using semantic analysis and take the values as weights of edges while sentences' values are scored by a variant of the traditional PageRank graph ranking algorithm considering both internal and external information. The experimental results show that the applicability of the model to text summarization is feasible and effective.

Text summarization using Sentence-Level Semantic Graph Model

Medical Meteorology is a rising Boundary Science. It is the study of atmospheric impact on physical, chemical and biological conditions of human bodies for treatments of disease and services of health care. This paper analyzes current situation in the field of medical meteorology and discusses the performance and the characteristic of Decision Tree algorithm on medical meteorology prediction based on existing forecasting algorithm. This paper also builds models according to weather elements to predict the incidence of the day, and further validations will test the accuracy of the predictions from the model. Advantages and disadvantages will also be then analyzed. Finally, strengths and weaknesses of other data mining algorithm are discussed based on the problems of Decision Tree Algorithm.

Analysis on meteorological conditions and health factors based on C4.5 algorithm

The paper presents an improved text similarity algorithm and applies to the Clinical Decision Support System. It can improve the efficiency of decision making. After analyzing the disadvantages of the conventional TF-IDF algorithm and Cosine Similarity calculation, we propose an improvement to the text similarity algorithm. The proposed algorithm takes into full consideration the impact of semantically-similar keywords and textually-similar keywords on text similarity, therefore achieves improved accuracy. The function of this Clinical Decision Support System is to search for relevant biomedical articles and locate solutions.

An improved text similarity algorithm research for clinical decision support system

To found security events from web logs has become an important aspect of network security. This paper proposes a website anomaly detection model based on security-log-analysis. After creating a anomaly feature sets of the model, C4.5 algorithm was used to improve feature sets, making the abnormal records in feature sets store hierarchically. Compared logs in website with the treated feature stes, the model ultimately achieves the purpose of checking website's security event fast and accurately.

Tao Lv

Papers

Text Summarization Using FrameNet-Based Semantic Graph Model

Text summarization using Sentence-Level Semantic Graph Model

Analysis on meteorological conditions and health factors based on C4.5 algorithm

An improved text similarity algorithm research for clinical decision support system

A model for website anomaly detection based on log analysis