Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles-猫眼课题宝

DOI：

10.18653/v1/d16-1001

发表时间：

2016-11

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

James Cross;Liang Huang

近年来，由于神经网络的出现，使用高效贪婪转换系统的解析精度得到了显著提高。尽管在依赖分析中取得了惊人的成果，但是，神经模型在选区分析中并没有超过最先进的方法。为了解决这个问题，我们引入了一个新的移位归约系统，其堆栈仅包含句子跨度，由最少的LSTM特征表示。我们还设计了第一个可证明的最优动态预言机用于选区解析，与标准依赖解析的O（n^3）预言机相比，它在摊销O（1）时间内运行。使用这个预言机进行训练，我们在英语和法语上都获得了最好的F1分数，这是任何不使用重新排序或外部数据的解析器的最好成绩。

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.

Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles

文献摘要

被引文献

相似文献