Parsing accuracy using efficient greedy transition systems has improved
dramatically in recent years thanks to neural networks. Despite striking
results in dependency parsing, however, neural models have not surpassed
state-of-the-art approaches in constituency parsing. To remedy this, we
introduce a new shift-reduce system whose stack contains merely sentence spans,
represented by a bare minimum of LSTM features. We also design the first
provably optimal dynamic oracle for constituency parsing, which runs in
amortized O(1) time, compared to O(n^3) oracles for standard dependency
parsing. Training with this oracle, we achieve the best F1 scores on both
English and French of any parser that does not use reranking or external data.

通过使用仅包含句子跨度的最小 LSTM 特征表示的新的 shift-reduce 系统以及第一个可以证明最优的动态 Oracle，该算法的时间复杂度是摊销 O（1），相比于标准依赖解析的 O（n ^ 3）Oracle，我们在使用这个 Oracle 进行训练后，在不使用重新排名或外部数据的情况下取得了最好的 F1 分数，而句法解析准确度得到了显著提高。