Increasing Student Engagement in Lessons and Assessing MOOC Participants Through Artificial Intelligence

Text Summarization based on Abstraction is the task of generating a concise summary that captures the principal ideas of the source text. It potentially contains new phrases that do not appear in the original text. Although it is widely studied for languages like English and French, owing to the scarcity of data on regional vernacular languages like Hindi, the research in this area is still in the primitive stages. We propose a novel approach for building an Abstractive Text Summarizer for Hindi corpus using the Transformer encoder-decoder architecture. Firstly, efficient pre-trained word representations are generated using Facebook’s fastText model. Next, the Transformer model is employed to extract contextual dependencies and yield better semantic representations for a morphologically rich language like Hindi, engendering an abstractive summary. On performing an experimental evaluation on the Hindi news dataset to generate news article headlines, we achieve a ROUGE-1 precision and recall score of 0.682 and 0.598, respectively, which outperforms the state-of-the-art techniques. 

Abstractive Text Summarization of Hindi Corpus Using Transformer Encoder-Decoder Model

Discourse structure analysis has shown to be useful for many artificial intelligence (AI) tasks such as text sum-marization and text categorization. However, for the Chinese news domain, the discourse structure analysis system is still immature due to the limitation of the lack of expert-annotated datasets. In this paper, we present CNA, a Chinese news corpus containing 1155 news articles annotated by human experts, which covers four domains and four news media sources. Next, we implement several text classification methods as baselines. Experimental results demonstrate that document-level method can achieve a better performance, and we further propose a document-level neural network model with multiple sentence features which achieves the state-of-the-art performance. In the end, we analyze the content type distribution of each sentence in CNA and the prediction errors of our model that occurred on the test set. The codes and dataset will be open-sourced at https://github.com/gzl98/Chinese_Discourse_Profiling. 

CNA: A Dataset for Parsing Discourse Structure on Chinese News Articles

The increased availability of online feedback or review tools, and the enormous amount of information on these platforms, have made text summarization a vital research area in natural language processing. Instead of potential consumers going through thousands of reviews to get needed information, summarization will enable them to see a concise form of a chunk of reviews with relevant information. News and scientific articles have been used in text summarization models. This study proposes a text summarization method based on the Text-to- Text Transfer Transformer (T5) model. We use the University of California, Irvine's (UCI) drug reviews dataset. We manually created human summaries for the ten most useful reviews of a particular drug for 500 different drugs from the dataset. We fine-tune the Text-to- Text Transfer Transformer (T5) model to perform abstractive text summarization. The model's effectiveness was evaluated using the ROUGE metrics, and our model achieved an average of ROUGE1, ROUGE2, and ROUGEL scores of 45.62, 25.58, and 36.53, respectively. We also fine-tuned this model on a standard dataset(BBC News Dataset) previously used for text summarization and got average ROUGE1, ROUGE2, and ROUGEL scores of 69.05, 59.70, and 52.97, respectively. 

Text Summarization using Transformer Model

The growing number of published academic literature poses challenges to the research community which struggles to keep up with the vast amount of publications through traditional research methods that are highly manual in nature. Researchers are struggling to determine the most relevant research gaps, yielding insignificant publications that constitute a waste of resources. As a consequence, AI applications are being applied increasingly to automate and facilitate the review process of these vast amounts of papers. However, scholars have so far only addressed a limited number of scientific fields and focused their efforts on one end of the spectrum in automating systematic literature reviews (SLRs). Yet, these are not sufficient to cover the full range of research questions and available data sources. This paper offers a comparative study of systematic and semi-systematic literature reviews to determine the potential of AI applications in both types of literature review processes. The analysis addresses the status quo and discusses apparent limitations of AI to automate reviews. Results are synthesized in proposing a new tool integrating various AI applications along the research process that improve the speed, quality, and cost-efficiency of the overall research process. 

The application of artificial intelligence on different types of literature reviews - A comparative study

The amount of text data available online is increasing at a very fast pace hence text summarization has become essential. Most of the modern recommender and text classification systems require going through a huge amount of data. Manually generating precise and fluent summaries of lengthy articles is a very tiresome and time-consuming task. Hence generating automated summaries for the data and using it to train machine learning models will make these models space and time-efficient. Extractive summarization and abstractive summarization are two separate methods of generating summaries. The extractive technique identifies the relevant sentences from the original document and extracts only those from the text. Whereas in abstractive summarization techniques, the summary is generated after interpreting the original text, hence making it more complicated. In this paper, we will be presenting a comprehensive comparison of a few transformer architecture based pre-trained models for text summarization. For analysis and comparison, we have used the BBC news dataset that contains text data that can be used for summarization and human generated summaries for evaluating and comparing the summaries generated by machine learning models.

Anushka Gupta

Papers

Automated News Summarization Using Transformers