Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation
Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation
复制标题
DOI：
10.1162/tacl_a_00451
复制
发表时间：
2022-02
影响因子：
10.9
通讯作者：
Noriki Nishida;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Noriki Nishida;Yuji Matsumoto
语篇解析的研究已经有几十年了。然而，将话语解析用于现实世界的应用仍然具有挑战性，因为域外文本的解析精度会显着降低。在本文中，我们报告并讨论了引导方法的有效性和局限性，该方法使现代基于 BERT 的话语依存解析器适应域外文本，而不依赖额外的人工监督。具体来说，我们研究了基于图和基于转换的话语依存解析模型的自训练、协同训练、三重训练和非对称三重训练，以及两种适应场景中的置信度测量和样本选择标准：科学学科之间的独白适应和对话体裁适应。我们还发布了 COVID-19 话语依存树库 (COVID19-DTB)，这是一种新的手动注释资源，用于生物医学论文摘要的话语依存解析。实验结果表明，引导对于语篇依存解析的无监督域适应具有显着且一致的效果，但准确预测的伪标签的低覆盖率是进一步改进的瓶颈。我们证明主动学习可以减轻这种限制。
Discourse parsing has been studied for decades. However, it still remains challenging to utilize discourse parsing for real-world applications because the parsing accuracy degrades significantly on out-of-domain text. In this paper, we report and discuss the effectiveness and limitations of bootstrapping methods for adapting modern BERT-based discourse dependency parsers to out-of-domain text without relying on additional human supervision. Specifically, we investigate self-training, co-training, tri-training, and asymmetric tri-training of graph-based and transition-based discourse dependency parsing models, as well as confidence measures and sample selection criteria in two adaptation scenarios: monologue adaptation between scientific disciplines and dialogue genre adaptation. We also release COVID-19 Discourse Dependency Treebank (COVID19-DTB), a new manually annotated resource for discourse dependency parsing of biomedical paper abstracts. The experimental results show that bootstrapping is significantly and consistently effective for unsupervised domain adaptation of discourse dependency parsing, but the low coverage of accurately predicted pseudo labels is a bottleneck for further improvement. We show that active learning can mitigate this limitation.