论文标题
基于快速规则的解码：神经选区解析中的句法规则
Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing
论文作者
论文摘要
关于神经选区解析的最新研究集中在编码器结构上，而很少有发展的发展。先前的研究表明，基于句法规则的概率统计方法在选区解析方面特别有效，而在训练神经模型中，在先前工作中未使用句法规则，这可能是由于其巨大的计算要求。在本文中，我们首先实施了一个快速的CKY解码程序来利用GPU加速度，基于该过程，我们进一步得出了基于句法规则（规则约束）CKY解码。在实验中，我们的方法分别在PTB和CTB的数据集上获得了95.89和92.52 F1，与以前的方法相比，这显示出显着改善。此外，我们的解析器在零拍设置中实现了强大而有竞争力的跨域性能。
Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders. Previous research has demonstrated that probabilistic statistical methods based on syntactic rules are particularly effective in constituency parsing, whereas syntactic rules are not used during the training of neural models in prior work probably due to their enormous computation requirements. In this paper, we first implement a fast CKY decoding procedure harnessing GPU acceleration, based on which we further derive a syntactic rule-based (rule-constrained) CKY decoding. In the experiments, our method obtains 95.89 and 92.52 F1 on the datasets of PTB and CTB respectively, which shows significant improvements compared with previous approaches. Besides, our parser achieves strong and competitive cross-domain performance in zero-shot settings.
