Common use of Agreement evaluation Clause in Contracts

Agreement evaluation. Table 3 compares how well two asymmetric models agree with each other among GIZA++, BERKELEY and our approach. We use F1 score to measure the degree of agreement: indirect supervision, which helps to train a more reasonable model with biased guidance. While agreement-based learning provides a principled approach to training a generative mod- el, it constrains that the sub-models must share the same output space. Our work extends (Liang et al., 2006) to introduce arbitrary loss functions that can encode prior knowledge. As a result, Liang et al. (2006)’s model is a special case of our frame- work. Another difference is that our framework allows for including the agreement between word alignment and other structures such as phrase seg- mentations and parse trees.