CATS: Customizable Abstractive Topic-based Summarization

Neural sequence-to-sequence models are the state-of-the-art approach used in abstractive summarization of textual documents, useful for producing condensed versions of source text narratives without being restricted to using only words from the original text. Despite the advances in abstractive summarization, custom generation of summaries (e.g., towards a user’s preference) remains unexplored. In this article, we present CATS, an abstractive neural summarization model that summarizes content in a sequence-to-sequence fashion while also introducing a new mechanism to control the underlying latent topic distribution of the produced summaries. We empirically illustrate the efficacy of our model in producing customized summaries and present findings that facilitate the design of such systems. We use the well-known CNN/DailyMail dataset to evaluate our model. Furthermore, we present a transfer-learning method and demonstrate the effectiveness of our approach in a low resource setting, i.e., abstractive summarization of meetings minutes, where combining the main available meetings’ transcripts datasets, AMI and International Computer Science Institute(ICSI) , results in merely a few hundred training documents.

Abstractive Arabic Text Summarization Based on Deep Learning

Text summarization (TS) is considered one of the most difficult tasks in natural language processing (NLP). It is one of the most important challenges that stand against the modern computer system’s capabilities with all its new improvement. Many papers and research studies address this task in literature but are being carried out in extractive summarization, and few of them are being carried out in abstractive summarization, especially in the Arabic language due to its complexity. In this paper, an abstractive Arabic text summarization system is proposed, based on a sequence-to-sequence model. This model works through two components, encoder and decoder. Our aim is to develop the sequence-to-sequence model using several deep artificial neural networks to investigate which of them achieves the best performance. Different layers of Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Bidirectional Long Short-Term Memory (BiLSTM) have been used to develop the encoder and the decoder. In addition, the global attention mechanism has been used because it provides better results than the local attention mechanism. Furthermore, AraBERT preprocess has been applied in the data preprocessing stage that helps the model to understand the Arabic words and achieves state-of-the-art results. Moreover, a comparison between the skip-gram and the continuous bag of words (CBOW) word2Vec word embedding models has been made. We have built these models using the Keras library and run-on Google Colab Jupiter notebook to run seamlessly. Finally, the proposed system is evaluated through ROUGE-1, ROUGE-2, ROUGE-L, and BLEU evaluation metrics. The experimental results show that three layers of BiLSTM hidden states at the encoder achieve the best performance. In addition, our proposed system outperforms the other latest research studies. Also, the results show that abstractive summarization models that use the skip-gram word2Vec model outperform the models that use the CBOW word2Vec model.

A Systematic Survey on Multi-document Text Summarization

Automatic text summarization is a technique of generating short and accurate summary of a longer text document. Text summarization can be classified based on the number of input documents (single document and multi-document summarization) and based on the characteristics of the summary generated (extractive and abstractive summarization). Multi-document summarization is an automatic process of creating relevant, informative and concise summary from a cluster of related documents. This paper does a detailed survey on the existing literature on the various approaches for text summarization. Few of the most popular approaches such as graph based, cluster based and deep learning-based summarization techniques are discussed here along with the evaluation metrics, which can provide an insight to the future researchers.

Text Summarizing Using NLP

In this era everything is digitalized we can find a large amount of digital data for different purposes on the internet and relatively it’s very hard to summarize this data manually. Automatic Text Summarization (ATS) is the subsequent big one that could simply summarize the source data and give us a short version that could preserve the content and the overall meaning. While the concept of ATS is started long back in 1950’s, this field is still struggling to give the best and efficient summaries. ATS proceeds towards 2 methods, Extractive and Abstractive Summarization. The Extractive and Abstractive methods had a process to improve text summarization technique. Text Summarization is implemented with NLP due to packages and methods in Python. Different approaches are present for summarizing the text and having few algorithms with which we can implement it. Text Rank is what to extractive text summarization and it is an unsupervised learning. Text Rank algorithm also uses undirected graphs, weighted graphs. keyword extraction, sentence extraction. So, in this paper, a model is made to get better result in text summarization with Genism library in NLP. This method improves the overall meaning of the phrase and the person reading it can understand in a better way.

Reducing repetition in convolutional abstractive summarization

Convolutional sequence to sequence (CNN seq2seq) models have met success in abstractive summarization. However, their outputs often contain repetitive word sequences and logical inconsistencies, limiting the practicality of their application. In this paper, we find the reasons behind the repetition problem in CNN-based abstractive summarization through observing the attention map between the summaries with repetition and their corresponding source documents and mitigate the repetition problem. We propose to reduce the repetition in summaries by attention filter mechanism (ATTF) and sentence-level backtracking decoder (SBD), which dynamically redistributes attention over the input sequence as the output sentences are generated. The ATTF can record previously attended locations in the source document directly and prevent the decoder from attending to these locations. The SBD prevents the decoder from generating similar sentences more than once via backtracking at test. The proposed model outperforms the baselines in terms of ROUGE score, repeatedness, and readability. The results show that this approach generates high-quality summaries with minimal repetition and makes the reading experience better.