首页> 外文会议>International conference on computational linguistics >Adapting taggers to Twitter with not-so-distant supervision
【24h】

Adapting taggers to Twitter with not-so-distant supervision

机译:在不太遥远的监督下使标记者适应Twitter

获取原文

摘要

We experiment with using different sources of distant supervision to guide unsupervised and semi-supervised adaptation of part-of-speech (POS) and named entity taggers (NER) to Twitter. We show that a particularly good source of not-so-distant supervision is linked websites. Specifically, with this source of supervision we are able to improve over the state-of-the-art for Twitter POS tagging (89.76% accuracy, 8% error reduction) and NER (F1=79.4%, 10% error reduction).
机译:我们尝试使用远程监督的不同来源来指导词性(POS)和命名实体标记(NER)的非监督和半监督适应Twitter。我们表明,链接的网站是不太远的监管的一个很好的来源。具体来说,借助这种监管来源,我们可以改善Twitter POS标签(准确度为89.76%,错误减少8%)和NER(F1 = 79.4%,错误减少10%)的最新技术。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号