缓解时间漂移:保持NER模型清晰的一种简单方法
Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp
摘要:
用于命名实体识别的神经模型的性能随着时间的推移而降低,变得陈旧。这种退化是由于时间漂移,即目标变量的统计特性随时间的变化。这个问题对于社交媒体数据来说尤其成问题,因为话题变化很快。为了缓解这个问题,数据注释和模型的重新训练是常见的。尽管它的有用性,这个过程是昂贵的和耗时的,这激发了新的研究有效的模型更新。在本文中,我们提出了一种直观的方法来衡量推文的潜在趋势,并使用此指标来选择最具信息量的实例用于训练。我们在时间Twitter数据集上对三种最先进的模型进行了实验。我们的方法显示出更大的提高预测精度与更少的训练数据比替代品,使其成为一个有吸引力的,实用的解决方案。
英文摘要:
Performance of neural models for named entity recognition degrades over time, becoming stale. This degradation is due to temporal drift, the change in our target variables' statistical properties over time. This issue is especially problematic for social media data, where topics change rapidly. In order to mitigate the problem, data annotation and retraining of models is common. Despite its usefulness, this process is expensive and time-consuming, which motivates new research on efficient model updating. In this paper, we propose an intuitive approach to measure the potential trendiness of tweets and use this metric to select the most informative instances to use for training. We conduct experiments on three state-of-the-art models on the Temporal Twitter Dataset. Our approach shows larger increases in prediction accuracy with less training data than the alternatives, making it an attractive, practical solution.
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。