当没有大写时,为ner和pos
ner and pos when nothing is capitalized
摘要:
对于那些使用大写的语言来说,大写是命名实体识别(NER)和词性(POS)标记的基本NLP任务的重要信号。事实上,这是一个如此强烈的信号,以至于在常见的小写场景中,例如嘈杂的Web文本或机器翻译输出,这些任务的模型性能急剧下降。在这项工作中,我们进行了系统的分析,解决这个问题,只修改外壳的训练或测试数据使用lowercasing和truecasing方法。虽然以前的工作和第一印象可能会建议训练一个无大小写的模型,或在测试时使用truecaser,我们表明,最有效的策略是一个串联的大小写和小写的训练数据,产生一个单一的模型与高性能的大小写和uncased文本。正如我们的实验所示,这一结果适用于任务和输入表示。最后,我们表明,我们提出的解决方案在噪声域外的Twitter数据的提及检测中提供了8%的F1改进。
英文摘要:
For those languages which use it, capitalization is an important signal for the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech (POS) tagging. In fact, it is such a strong signal that model performance on these tasks drops sharply in common lowercased scenarios, such as noisy web text or machine translation outputs. In this work, we perform a systematic analysis of solutions to this problem, modifying only the casing of the train or test data using lowercasing and truecasing methods. While prior work and first impressions might suggest training a caseless model, or using a truecaser at test time, we show that the most effective strategy is a concatenation of cased and lowercased training data, producing a single model with high performance on both cased and uncased text. As shown in our experiments, this result holds across tasks and input representations. Finally, we show that our proposed solution gives an 8% F1 improvement in mention detection on noisy out-of-domain Twitter data.
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。