%0 Conference Proceedings %T A Minimal Span-Based Neural Constituency Parser %A Stern, Mitchell %A Andreas, Jacob %A Klein, Dan %Y Barzilay, Regina %Y Kan, Min-Yen %S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) %D 2017 %8 July %I Association for Computational Linguistics %C Vancouver, Canada %F stern-etal-2017-minimal %X In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with classical dynamic programming techniques, but also admits a novel greedy top-down inference algorithm based on recursive partitioning of the input. We demonstrate empirically that both prediction schemes are competitive with recent work, and when combined with basic extensions to the scoring model are capable of achieving state-of-the-art single-model performance on the Penn Treebank (91.79 F1) and strong performance on the French Treebank (82.23 F1). %R 10.18653/v1/P17-1076 %U https://aclanthology.org/P17-1076 %U https://doi.org/10.18653/v1/P17-1076 %P 818-827