While the task of language generation seems to separate quite naturally into the two aspects of language generation (text planning and text production), it is necessary to have the planning and the production interact at generator decision points in such a way that the former need not contain explicit syntactic knowledge, and that the latter need not contain explicit goal-related information. T...

The ability to generate narrative is of importance to computer systems that wish to use story effectively for entertainment, training, or education. One way to generate narrative is to use planning. However, story planners are limited by the fact that they can only operate on the story world provided, which impacts the ability of the planner to find a solution story plan and the quality and str...

ERP implementations have flounced/swept from side to side the business zone from the very beginning since 1990s, serving companies to oblige losing/down outlays and maneuver further well and powerfully. ERP has permitted sectors/division heads to scrutiny their concern data more straightforwardly and cope it more in point of fact. It furthermore has modernized a host of manufacturing/industrial...

In this paper we examine the general problem of generating preferred explanations for observed behavior with respect to a model of the behavior of a dynamical system. This problem arises in a diversity of applications including diagnosis of dynamical systems and activity recognition. We provide a logical characterization of the notion of an explanation. To generate explanations we identify and ...

Existing models for sampling the space of all planning problems produce both solvable and unsolvable instances. In particular, when attempting to identify very hard ones, one encounters both, as the hardness in the standard models is accompanied by the possibility of an instance being solvable or unsolvable. This is a disadvantage of the standard models, because of the strong asymmetry of plann...

Neural data-to-text generation models have achieved significant advancement in recent years. However, these two shortcomings: the generated texts tend to miss some vital information, and they often generate descriptions that are not consistent with structured input data. To alleviate problems, we propose a model Dynamic content Planning, named NDP 2for abbreviation. The can utilize previously t...