We present new supertaggers trained on HPSG-based treebanks. These treebanks
feature high-quality annotation based on a well-developed linguistic theory and
include diverse and challenging test datasets, beyond the usual WSJ section 23
and Wikipedia data. HPSG supertagging has previously relied on MaxEnt-based
models. We use SVM and neural CRF- and BERT-based methods and show that both
SVM and neural supertaggers achieve considerably higher accuracy compared to
the baseline. Our fine-tuned BERT-based tagger achieves 97.26% accuracy on 1000
sentences from WSJ23 and 93.88% on the completely out-of-domain The Cathedral
and the Bazaar (cb)). We conclude that it therefore makes sense to integrate
these new supertaggers into modern HPSG parsers, and we also hope that the
diverse and difficult datasets we used here will gain more popularity in the
field. We contribute the complete dataset reformatted for token classification.

我们提出了基于 HPSG 的新型超标注模型，通过 SVM 和神经网络方法在高质量标注的树库上进行训练，与基线相比，SVM 和神经超标注模型都取得了明显更高的准确性。我们的 BERT 超标注模型在 WSJ23 数据集和 Cathedral and the Bazaar 数据集上分别达到了 97.26% 和 93.88% 的准确率。因此，将这些新型超标注模型整合到现代 HPSG 解析器中是有意义的，并且希望我们在这里使用的多样而困难的数据集能在该领域中获得更多的关注。我们还提供了完整的数据集，格式化用于标记分类。

HPSG 超标记再审视

Revisiting Supertagging for HPSG

Previous CCG supertaggers usually predict categories using multi-class
classification. Despite their simplicity, internal structures of categories are
usually ignored. The rich semantics inside these structures may help us to
better handle relations among categories and bring more robustness into
existing supertaggers. In this work, we propose to generate categories rather
than classify them: each category is decomposed into a sequence of smaller
atomic tags, and the tagger aims to generate the correct sequence. We show that
with this finer view on categories, annotations of different categories could
be shared and interactions with sentence contexts could be enhanced. The
proposed category generator is able to achieve state-of-the-art tagging (95.5%
accuracy) and parsing (89.8% labeled F1) performances on the standard CCGBank.
Furthermore, its performances on infrequent (even unseen) categories,
out-of-domain texts and low resource language give promising results on
introducing generation models to the general CCG analyses.

通过生成类别而不是分类类别，我们提出了一种新的 CCG supertagger 方法，将每个类别分解为一系列更小的标记，以此更好地处理类别间的关系并增强与句子上下文的交互。该方法能够在标准 CCGBank 上实现最先进的标识 (95.5% 精确度) 和分析 (89.8% 标记 F1)，并在罕见类别、领域外文本和资源匮乏语言方面取得了有希望的结果。