Most e-learning systems engage successively students in reading, writing and assessment activities. In the third phase, the teacher gives feedback on student comprehension, which is often processed a long time after the others, letting the students alone with their difficulties. Thus, there is room to devise automated assessment systems on course comprehension, based on NLP techniques such as latent semantic analysis (LSA). The aim of this paper is to present some systems devised to complete this aim, which implement LSA to model learners' comprehension and/or to compare reading material (e.g., course text) with learners' summaries about it, select reading materials and predict student processes from their summaries.