Generation of Formal and Informal Sentences

This paper addresses the task of using natural language generation (NLG) techniques to generate sentences with formal and with informal style. We studied the main characteristics of each style, which helped us to choose parameters that can produce sentences in one of the two styles. We collected some ready-made parallel list of formal and informal words and phrases, from different sources. In addition, we added two more parallel lists: one that contains most of the contractions in English (short forms) and their full forms, and another one that consists in some common abbreviations and their full forms. These parallel lists might help to generate sentences in the preferred style, by changing words or expressions for that style. Our NLG system is built on top of the SimpleNLG package (Gatt and Reiter, 2009). We used templates from which we generated valid English texts with formal or informal style. In order to evaluate the quality of the generated sentences and their level of formality, we used human judges. The evaluation results show that our system can generate formal and informal style successfully, with high accuracy. The main contribution of our work consists in designing a set of parameters that led to good results for the task of generating texts with different formality levels.