... paper, we formulate ex-tractive summarization as a two step learn-ing problem building a generative model for pattern discovery and a regressionmodel for inference. We calculate scores for sentences ... provided for training summarization models and measuring theperformance of machine generated summaries.Extractive summarization methods can be clas-sified into two groups: supervised methods ... probabil-ity over all words vlassigned to topic zomat levell, by sampling only for words in wom,l. Similarly,psn,l= p(wsn,l|zsn, com, vl) is the probability ofwords wsnin...