Learning Linear Precedence Rules

A system is descril)ed which learns fl'om examples the Linear Precedence rules in an Immedia te Dominance/Linear Precedence grammar . Given a particular hnmediate Dominance g rammar and hierarchies of feature values potentially rel evant for linearization (=the systelu's bias), the leanler generates appropriate naturM language expressions to be ewduated as positive or negative by a teacher, and produces as output IAnear Precedence rules which can be directly used 1)y the gralnmar. 1 I n t r o d u c t i o n The lnanual cotnpilation of a. sizable g rammar is a difficult and t ime-consuming task. An important subtask is the construction of word ordering rules in the grammar . '[ 'hough some languages are proclaimed as having simple ordering rules, e.g. either complete scrambling or strictly "fixed" order, most languages exhibit quite complex regularities (Steele, 198l), and even the rigid word order languages (like 1,;nglish) and those with to tal scrambling (like Warlpiri; cf. (H ale, 1983) may show intricate rules (Kashket, 11981); hence the need for their automat ic acquisition. 'Fhis I;ask however, to the best of our knowledge, has not heen previously addressed. This paper describes a prograln which, given a g rammar with no ordering relations, l)roduces as outpu_t a set of linearization, or Linear Precedence, rules which can be directly employed by that grammar. The learning step uses the version space algorithm, a familiar techlfique from ma.chine learning for learning from examples. In contrast to most previous uses of the algorithnl for various learning tasks, which rely on priorly given classified examples, our learner generates itself tile training instances olte at a tinie, and they are then classed as positive or negative by a teacher. A selective generation of training instances is employe, d which facilitates the learning by minimizing the nu,nl)er of evaluations that the teacher