Here, we describe the generative process our model uses to generate the observed utterances and present the corresponding graphical model.

For clarity, we assume that the values of the boundary variables bi are given in the generative process .

The generative process indicates that our model ignores utterance boundaries and views the entire data as concatenated spoken segments.

In the next section, we show the generative process our model uses to generate the observed data.

We inject information extracted from unstructured web search query logs as prior information to enhance the generative process of the natural language utterance understanding model.

This is because we utilize domain priors obtained from the web sources as supervision during generative process as well as unlabeled utterances that enable handling language variability.

The generative process of our multilayer context model (MCM) (Fig.

We assume the following generation process for all the posts in the stream.

Figure 2: The generation process for all posts.

Formally, the generation process is summarized in Figure 2.

We cast the generation process as constraint optimization problems, collectively incorporating multiple interconnected aspects of language composition for content planning, surface realization and discourse structure.

Because the generation process sticks relatively closely to the recognized content, the resulting descriptions often lack the kind of coverage, creativity, and complexity typically found in human-written text.

Our ILP formulation encodes a rich set of linguistically motivated constraints and weights that incorporate multiple aspects of the generation process .