No abstract

No abstract

Modelling ethics is critical to understanding and analysing social phenomena. However, prior literature either incorporates ethics into agent strategies or uses it for evaluation of agent behaviour. This work proposes a framework that models both, ethical decision making as well as evaluation using virtue ethics and utilitarianism. In an iteration, agents can use either the classical Continuous Prisoner's Dilemma or a new type of interaction called moral interaction, where agents donate or steal from other agents. We introduce moral interactions to model ethical decision making. We also propose a novel agent type, called virtue agent, parametrised by the agent's level of ethics. Virtue agents' decisions are based on moral evaluations of past interactions. Our simulations show that unethical agents make short term gains but are less prosperous in the long run. We find that in societies with positivity bias, unethical agents have high incentive to become ethical. The opposite is true of societies with negativity bias. We also evaluate the ethicality of existing strategies and compare them with those of virtue agents.

Code-Mixed language plays a very important role in communication in multilingual societies and with the recent increase in internet users especially in multilingual societies, the usage of such mixed language has also increased. However, the cross translation between the Hinglish Code-Mixed and English and vice-versa has not been explored very extensively. With the recent success of large pretrained language models, we explore the possibility of using multilingual pretrained transformers like mBART and mT5 for exploring one such task of code-mixed Hinglish to English machine translation. Further, we compare our approach with the only baseline over the PHINC dataset and report a significant jump from 15.3 to 29.5 in BLEU scores, a 92.8% improvement over the same dataset.

Word emphasis in textual content aims at conveying the desired intention by changing the size, color, typeface, style (bold, italic, etc.), and other typographical features. The emphasized words are extremely helpful in drawing the readers' attention to specific information that the authors wish to emphasize. However, performing such emphasis using a soft keyboard for social media interactions is time-consuming and has an associated learning curve. In this paper, we propose a novel approach to automate the emphasis word detection on short written texts. To the best of our knowledge, this work presents the first lightweight deep learning approach for smartphone deployment of emphasis selection. Experimental results show that our approach achieves comparable accuracy at a much lower model size than existing models. Our best lightweight model has a memory footprint of 2.82 MB with a matching score of 0.716 on SemEval-2020 (shallowLearner, 2020) public benchmark dataset.