This paper introduces tree transducers as a unifying theory for semantic parsing models based on tree transformations. Many existing models use tree transformations, but implement specialized training and smoothing methods, which makes it difficult to modify or extend the models. By connecting to the rich literature on tree automata, we show how semantic parsing models can be developed using completely general estimation methods. We demonstrate the approach by reframing and extending one state-of-the-art model as a tree automaton. Using a variant of the inside-outside algorithm with variational Bayesian estimation, our generative model achieves higher raw accuracy than existing generative and discriminative approaches on a standard data set.
|Number of pages||10|
|Journal||Proceedings of the Australasian Language Technology Association Workshop 2011|
|Publication status||Published - 2011|
|Event||Australasian Language Technology Workshop (9th : 2011) - Canberra|
Duration: 1 Dec 2011 → 2 Dec 2011