Integrative Semantic Dependency Parsing via Efficient Large-scale Feature Selection
This work addresses the need for more integrated and practical semantic parsing systems for natural language processing applications, though it is incremental as it builds on existing classification approaches.
The paper tackles semantic dependency parsing by integrating all subtasks into a single model using a maximum entropy classifier with adaptive pruning and large-scale feature selection, achieving state-of-the-art performance on the CoNLL-2008 dataset, outperforming all but one top pipeline system.
Semantic parsing, i.e., the automatic derivation of meaning representation such as an instantiated predicate-argument structure for a sentence, plays a critical role in deep processing of natural language. Unlike all other top systems of semantic dependency parsing that have to rely on a pipeline framework to chain up a series of submodels each specialized for a specific subtask, the one presented in this article integrates everything into one model, in hopes of achieving desirable integrity and practicality for real applications while maintaining a competitive performance. This integrative approach tackles semantic parsing as a word pair classification problem using a maximum entropy classifier. We leverage adaptive pruning of argument candidates and large-scale feature selection engineering to allow the largest feature space ever in use so far in this field, it achieves a state-of-the-art performance on the evaluation data set for CoNLL-2008 shared task, on top of all but one top pipeline system, confirming its feasibility and effectiveness.