再现“没有大写时的名词和名词”
reproducing "ner and pos when nothing is capitalized"
摘要:
大写是许多NLP任务中的重要特征,例如命名实体识别(NER)或词性标注(POS)。我们试图重现论文的结果,该论文展示了当训练数据和测试数据之间的套管不匹配时如何减轻显着的性能下降。特别是,我们表明,小写50%的数据集提供了最佳的性能,匹配的索赔原始文件。我们还表明,在我们试图重现的几乎所有实验中,我们的表现都略低,这表明可能有一些隐藏的因素影响我们的表现。最后,我们将所有的工作都放在一个公共的github仓库中。
英文摘要:
Capitalization is an important feature in many NLP tasks such as Named Entity Recognition (NER) or Part of Speech Tagging (POS). We are trying to reproduce results of paper which shows how to mitigate a significant performance drop when casing is mismatched between training and testing data. In particular we show that lowercasing 50% of the dataset provides the best performance, matching the claims of the original paper. We also show that we got slightly lower performance in almost all experiments we have tried to reproduce, suggesting that there might be some hidden factors impacting our performance. Lastly, we make all of our work available in a public github repository.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。