In this paper, we show how these results can be exploited to improve parsing accuracy by integrating a graph-based and a transition-based model.

For the graph-based model, X is the set of possible dependency arcs (2,7,1); for the transition-based model, X is the set of possible configuration-transition pairs (0,75).

3.2 The Guided Graph-Based Model

Practically all data-driven models that have been proposed for dependency parsing in recent years can be described as either graph-based or transition-based (McDonald and Nivre, 2007).

In graph-based parsing, we learn a model for scoring possible dependency graphs for a given sentence, typically by factoring the graphs into their component arcs, and perform parsing by searching for the highest-scoring graph.

The graph-based models are globally trained and use exact inference algorithms, but define features over a limited history of parsing decisions.

2.2 Graph-Based Models

Graph-based dependency parsers parameterize a model over smaller substructures in order to search the space of valid dependency graphs and produce the most likely one.

An advantage of graph-based methods is that tractable inference enables the use of standard structured learning techniques that globally set parameters to maximize parsing performance on the training set (McDonald et al., 2005a).

Second, we use two graph-based summarization approaches, Generalized ClueWordSummarizer and Page-Rank, to extract sentences as summaries.

Third, we propose a summarization approach based on subjective opinions and integrate it with the graph-based ones.

Finally, we did not compared CWS to other possible graph-based approaches as we propose in this paper.

Other than the conversation structure, the measures of cohesion and the graph-based summarization methods we have proposed, the importance of a sentence in emails can be captured from other aspects.