In recent years, significant progress has been made in text generation. The latest text generation models are revolutionizing the domain by generating human-like text. It has gained wide popularity recently in many domains like news, social networks, movie script writing, poetry composition, to name a few. The application of text generation in various fields has resulted in a lot of interest from the scientific community in this area. To the best of our knowledge, there is a lack of extensive review and up-to-date body of knowledge of text generation deep learning models. Therefore, this paper aims to bring together all the relevant work in a systematic mapping study highlighting key contributions from various researchers over the years, focusing on the past, present, and future trends. In this work, we have identified 90 primary studies from 2015 to 2021 employing the PRISMA framework. We also identified research gaps that are further needed to be explored by the research community. In the end, we provide some future directions for researchers and guidelines for practitioners based on the findings of this review.

In the field of text classification, researchers have repeatedly shown the value of transformer-based models such as Bidirectional Encoder Representation from Transformers (BERT) and its variants. Nonetheless, these models are expensive in terms of memory and computational power but these models have not been utilized to classify long documents of several domains. In addition, these models are also often pre-trained on generalized languages, making them less effective in language-specific domains, such as legal documents. In the natural language processing (NLP) domain, there is a growing interest in creating newer models that can handle more complex input sequences and domain-specific languages. Keeping the power of NLP in mind, this study proposes a legal documentation classifier that classifies the legal document by using the sliding window approach to increase the maximum sequence length of the model. We used ECHR (European Court of Human Rights) publicly available dataset which to a large extent is imbalanced. Therefore, to balance the dataset we have scrapped the case articles from the web and extracted the data. Then, we employed conventional machine learning techniques such as SVM, DT, NB, AdaBoost, and transformer-based neural networks models including BERT, Legal-BERT, RoBERTa, BigBird, ELECTRA, and XLNet for the classification task. The experimental findings show that RoBERTa outperformed all the mentioned BERT versions by obtaining precision, recall, and F1-score of 89.1%, 86.2%, and 86.7%, respectively. While from conventional machine learning techniques, AdaBoost outclasses SVM, DT, and NB by achieving scores of 81.9%, 81.5%, and 81.7% for precision, recall, and F1-score, respectively.

Honey is a high-demand product in many countries because it is high in nutritional value and rich in antioxidants. Thus, the demand for honey is increased. However, the productivity of honey is naturally lower than its demand. Therefore, honey has often become a target for adulteration. Adulteration of honey is a critical issue because the nutritional value of pure honey is reduced by adding cheap and easily available sweeteners, affecting the consumers’ health. Thus, investigating honey authenticity is popular among regulatory bodies, the food industry, retail sellers, and consumers. Several works have been done to predict the authenticity of honey using various physicochemical features. Few other works have also classified honey on the basis of geographical or botanical origin. However, previous studies have three major limitations. First, the existing studies used the imbalanced datasets, and the performance of these studies further needs attention. Second, as far as we know, no researcher has attempted to use machine learning approaches in investigating the adulteration of Pakistani honey. Finally, the dataset for predicting the authenticity of Pakistani honey is lacking. Therefore, this study proposes a novel classification model to address the aforementioned weaknesses by classifying the authenticity of Pakistani honey using machine learning algorithms and several physicochemical features. This work also presents three classification models systematically to classify the Pakistani honey into three levels. The first level classifies whether the honey is original or branded. The second level classifies the geographical origin. The botanical origin of honey is classified in the third level. Our experimental results show that the proposed features coupled with machine learning algorithms can predict the authenticity of Pakistani honey with outstanding results. We believe that our proposed work will be proved beneficial in reducing the adulteration of Pakistani honey.