Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controlling several stylistic aspects of the generated text, in addition to its content. The method is based on conditioned RNN language model, where the desired content as well as the stylistic parameters serve as conditioning contexts. We demonstrate the approach o...

A probabilistic approach to interpretation of natural language utterances in terms of dialogue acts is proposed. It is illustrated how using Bayesian Networks, partial information obtained from an NLP component can be combined with knowledge the agent has about the state of the dialogue and about the user, in order to find the most probable dialogue act made.

Abstract Is Atlantic Multidecadal Oscillation a genuine representation of natural variability in the climate system? Or perhaps is it strongly forced by external drivers? In this paper, data-driven attribution investigation has been performed for (AMO) behaviour past via machine learning technique, NN modelling. We clearly see nature AMO last 150 years, with strong contribution forcing coming f...

During the past few years, modeling in agriculture has attracted considerable attention. New modeling methods including neural networks are employed in various industries, and it is necessary that their use in agriculture be also considered. This research addressed the trend of energy use in broiler farms in Alborz Province and sought to model the trend of energy consumption and production in t...

There are two dominant approaches to describe and understand the anatomy of complete health and well-being systems internationally. Yet, neither approach has been able to either predict or explain occasional but dramatic crises in health and well-being systems around the world and in developed emerging market or developing country contexts. As the impacts of such events can be measured not simp...

Traditional approaches to the problem of extracting data from texts have emphasized handcrafted linguisti c knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of a DARPA-funded research effort on integrating probabilistic language models with more traditiona l linguistic techniques . Our research and development goals are • more rapid de...