Two prevalent transfer learning approaches are used in recent works to improve neural networks performance for domains with small amounts of annotated data: Multi-task learning which involves training the task of interest with related auxiliary tasks to exploit their underlying similarities, and Mono-task fine-tuning, where the weights of the model are initialized with the pretrained weights of a large-scale labeled source domain and then fine-tuned with labeled data of the target domain (domain of interest). In this paper, we propose a new approach which takes advantage from both approaches by learning a hierarchical model trained across multiple tasks from a source domain, and is then fine-tuned on multiple tasks of the target domain. Our experiments on four tasks applied to the social media domain show that our proposed approach leads to significant improvements on all tasks compared to both approaches.

Neural Machine Translations (NMT) models are capable of translating a single bilingual pair and require a new model for each new language pair. Multilingual Neural Machine Translation models are capable of translating multiple language pairs, even pairs which it hasn’t seen before in training. Availability of parallel sentences is a known problem in machine translation. Multilingual NMT model leverages information from all the languages to improve itself and performs better. We propose a data augmentation technique that further improves this model profoundly. The technique helps achieve a jump of more than 15 points in BLEU score from the multilingual NMT model. A BLEU score of 36.2 was achieved for Sindhi–English translation, which is higher than any score on the leaderboard of the LoResMT SharedTask at MT Summit 2019, which provided the data for the experiments.

In sentiment analysis, several researchers have used emoji and hashtags as specific forms of training and supervision. Some emotions, such as fear and disgust, are underrepresented in the text of social media. Others, such as anticipation, are absent. This research paper proposes a new dataset for complex emotion detection using a combination of several existing corpora in order to represent and interpret complex emotions based on the Plutchik’s theory. Our experiments and evaluations confirm that using Transfer Learning (TL) with a rich emotional corpus, facilitates the detection of complex emotions in a four-dimensional space. In addition, the incorporation of the rule on the reverse emotions in the model’s architecture brings a significant improvement in terms of precision, recall, and F-score.