Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories
Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories
复制标题
DOI：
10.1162/tacl_a_00364
复制
发表时间：
2020-12
影响因子：
10.9
通讯作者：
Jakob Prange;Nathan Schneider;Vivek Srikumar
中科院分区：
文献类型：
--
作者：
Jakob Prange;Nathan Schneider;Vivek Srikumar
摘要尽管目前的CCG超级标记器在标准的WSJ测试集上达到了很高的准确率，但很少有系统利用范畴的内部结构来驱动句法分析过程中的句法推导。标记集传统上被截断，在长尾中丢弃了许多稀有和复杂的类别类型。然而，超级标签本身就是树。我们没有放弃稀有标签，而是研究了解释其内部结构的建设性模型，包括树形结构预测的新方法。我们最好的标签器能够恢复相当大一部分长尾超标签，甚至生成在训练中从未见过的CCG类别，同时用更少的参数在总体标签精度方面接近现有技术水平。我们进一步调查了不同的方法对域外评估集的推广情况。
Abstract Although current CCG supertaggers achieve high accuracy on the standard WSJ test set, few systems make use of the categories’ internal structure that will drive the syntactic derivation during parsing. The tagset is traditionally truncated, discarding the many rare and complex category types in the long tail. However, supertags are themselves trees. Rather than give up on rare tags, we investigate constructive models that account for their internal structure, including novel methods for tree-structured prediction. Our best tagger is capable of recovering a sizeable fraction of the long-tail supertags and even generates CCG categories that have never been seen in training, while approximating the prior state of the art in overall tag accuracy with fewer parameters. We further investigate how well different approaches generalize to out-of-domain evaluation sets.