Comparing and Combining Finite-State and Context-Free Parsers

In this paper, we look at comparing highaccuracy context-free parsers with highaccuracy finite-state (shallow) parsers on several shallow parsing tasks. We show that previously reported comparisons greatly under-estimated the performance of context-free parsers for these tasks. We also demonstrate that contextfree parsers can train effectively on relatively little training data, and are more robust to domain shift for shallow parsing tasks than has been previously reported. Finally, we establish that combining the output of context-free and finitestate parsers gives much higher results than the previous-best published results, on several common tasks. While the efficiency benefit of finite-state models is inarguable, the results presented here show that the corresponding cost in accuracy is higher than previously thought.