Discourse relations can occur both across sentences inter-sentential and within sentences intra-sentential , and more than one discourse relation can hold between the same units.
The availability of corpora has led to significant advances in training semantic parsers in English.
Here we show that while this can complicate the problem of identifying the location of implicit discourse relations, it can in turn simplify the problem of identifying their senses.
Two ranking methods are presented in this paper: a discrepancy ranking and an entropy ranking.