Bengali Abstractive News Summarization (BANS): A Neural Attention Approach (original) (raw)
Related papers
Bengali Abstractive News Summarization Using Seq2Seq Learning with Attention
Cyber Intelligence and Information Retrieval, 2021
Text summarization is the technique for generating short and succinct summaries from long texts that focuses on the most important information but keeps the overall exhaustive signification of the whole text. This paper presents a method of generating short abstractive summaries from long Bengali news articles using some basic NLP approaches with various Recurrent Neural Network (RNN) architectures, such as Bidirectional RNN, Encoder-Decoder RNN, Sequence to Sequence (Seq2Seq) Learning with Attention mechanism, Longest Short-term Memory (LSTM), etc. Dataset collected by the authors from different Bengali online newspapers is used here. Then, the dataset is preprocessed. After that, word embedding and vocabulary counts are done. Finally, the deep learning approaches are applied to generate an abstractive summary for each news article. The model used the Seq2Seq algorithm with an attention mechanism which reduced the training loss up to 0.001 successfully. Another existing dataset is used to evaluate the results and found satisfactory results for own dataset than the other.
Attention based Recurrent Neural Network for Nepali Text Summarization
Journal of Institute of Science and Technology
Automatic text summarization has been a challenging topic in natural language processing (NLP) as it demands preserving important information while summarizing the large text into a summary. Extractive and abstractive text summarization are widely investigated approaches for text summarization. In extractive summarization, the important sentence from the large text is extracted and combined to create a summary whereas abstractive summarization creates a summary that is more focused on meaning, rather than content. Therefore, abstractive summarization gained more attention from researchers in the recent past. However, text summarization is still an untouched topic in the Nepali language. To this end, we proposed an abstractive text summarization for Nepali text. Here, we, first, create a Nepali text dataset by scraping Nepali news from the online news portals. Second, we design a deep learning-based text summarization model based on an encoder-decoder recurrent neural network with at...
2021 24th International Conference on Computer and Information Technology (ICCIT), 2021
Despite the success of the neural sequenceto sequence model for abstractive text summarization, it has a few shortcomings, such as repeating inaccurate factual details and tending to repeat themselves. We propose a hybrid pointer generator network to solve the shortcomings of reproducing factual details inadequately and phrase repetition. We augment the attentionbased sequencetosequence using a hybrid pointer generator network that can generate OutofVocabulary words and enhance accuracy in reproducing authentic details and a coverage mechanism that discourages repetition. It produces a reasonablesized output text that preserves the conceptual integrity and factual information of the input article. For evalu ation, we primarily employed "BANSData" 1 a highly adopted publicly available Bengali dataset. Additionally, we prepared a largescale dataset called "BANS133" which consists of 133k Bangla news articles associated with humangenerated sum maries. Experimenting with the proposed model, we achieved ROUGE1 and ROUGE2 scores of 0.66, 0.41 for the BANSData" dataset and 0.67, 0.42 for the BANS133k" dataset, respectively. We demonstrated that the proposed system surpasses previous stateoftheart Bengali abstractive summarization techniques and its stability on a larger dataset. "BANS133" datasets and codebase will be publicly available for research.
Neural Attention Model for Abstractive Text Summarization Using Linguistic Feature Space
IEEE Access
Summarization generates a brief and concise summary which portrays the main idea of the source text. There are two forms of summarization: abstractive and extractive. Extractive summarization chooses important sentences from the text to form a summary whereas abstractive summarization paraphrase using advanced and nearer-to human explanation by adding novel words or phrases. For a human annotator, producing summary of a document is time consuming and expensive because it requires going through the long document and composing a short summary. An automatic feature-rich model for text summarization is proposed that can reduce the amount of labor and produce a quick summary by using both extractive and abstractive approach. A feature-rich extractor highlights the important sentences in the text and linguistic characteristics are used to enhance results. The extracted summary is then fed to an abstracter to further provide information using features such as named entity tags, part of speech tags and term weights. Furthermore, a loss function is introduced to normalize the inconsistency between word-level and sentencelevel attentions. The proposed two-staged network achieved a ROUGE score of 37.76% on the benchmark CNN/DailyMail dataset, outperforming the earlier work. Human evaluation is also conducted to measure the comprehensiveness, conciseness and informativeness of the generated summary.
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, 2016
In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling keywords , capturing the hierarchy of sentence-toword structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.
Summary Generation Using Deep Learning
IEEE EXPLORE, 2021
Summarization is the process of converting any given long text into a lossy compressed version while preserving the overall essence and meaning of the original given text. A problem in natural language processing is the task of summarizing a voluminous text. This research, lays emphasis on abstractive summarization of the text, a process which generates a coherent, short and meaningful text by learning the context from given input source text. This work is a preliminary attempt to generate abstractive summary. The proposed work uses the Attentional Encoder and Decoder based Sequence to Sequence Recurrent Neural Network model. The proposed research's primary objective is to get insights on the working of the mentioned Sequence architecture and the intricacies of different subcomponents of the encoders and the decoders architecture working together so as to give a particular end result. The scope of this paper covers an experimentation of performing text summarization process using Encoder and Decoder based Sequential Learning Recurrent Neural Network design. Satisfactory summary results are obtained after the model is experimented and analyzed on the Amazon Fine Food reviews.
A Bengali Text Summarization Using Encoder-Decoder Based on Social Media Dataset
Advances in Intelligent Systems and Computing, 2021
Text summarization is one of the strategies of compressing a long document to create a version of the main points of the original text. Due to the excessive amount of long posts these days, the value of summarization is born. Reading the main document and obtaining a desirable summary, time and trouble are worth it. Using machine learning and natural language processing built an automated text summarization system can solve this problem. So our proposed system will distribute an abstractive summary of a long text automatically in a period of some time. We have done the whole analysis with the Bengali text. In our designed model, we used chain to chain models of RNN with LSTM in the encrypting layer. The architecture of our model works using RNN decoder and encoder, where the encoder inputs text document and generates output as a short summary at the decoder. This system improves two things, namely summarization and establishing benchmarks performance with ignoble train loss. To train our model, we use our dataset that was created from various online media, articles, Facebook, and some people's personal posts. The challenges we face most here are Bengali text processing, limited text length, enough resources for collecting text.
Improving Neural Abstractive Text Summarization with Prior Knowledge (Position Paper)
International Conference of the Italian Association for Artificial Intelligence, 2016
ive text summarization is a complex task whose goal is to generate a concise version of a text without necessarily reusing the sentences from the original source, but still preserving the meaning and the key contents. In this position paper we address this issue by modeling the problem as a sequence to sequence learning and exploiting Recurrent Neural Networks (RNN). Moreover, we discuss the idea of combining RNNs and probabilistic models in a unified way in order to incorporate prior knowledge, such as linguistic features. We believe that this approach can obtain better performance than the state-of-the-art models for generating well-formed summaries.
Journal of Applied Research and Technology
With the rise of the Internet, we now have a lot of information at our disposal. We 're swamped from many sources — news, social media, to name a few, office emails. This paper addresses the problem of reading through such extensive information by summarizing it using text summarizer based on ive Summarization using deep learning models, i.e. using bidirectional Long Short-Term Memory (LSTM) networks and Pointer Generator mode. The LSTM model (which is a modification of the Recurrent Neural Network) is trained and tested on the Amazon Fine Food Review dataset using the Bahadau Attention Model Decoder with the use of Conceptnet Numberbatch embeddings that are very similar and better to GloVe. Pointer Generator mode is trained and tested by the CNN / Daily Mail dataset and the model uses both Decoder and Attention inputs. But due 2 major problems in LSTM model like the inability of the network to copy facts and repetition of words the second method is, i.e., Pointer Generator mode...