Traditional text classifiers are limited to predicting over a fixed set of labels. However, in many real-world applications the label set is frequently changing. For example, in intent classification, new intents may be added over time while others are removed. We propose to address the problem of dynamic text classification by replacing the traditional, fixed-size output layer with a learned, semantically meaningful metric space. Here the distances between textual inputs are optimized to perform nearest-neighbor classification across overlapping label sets. Changing the label set does not involve removing parameters, but rather simply adding or removing support points in the metric space. Then the learned metric can be fine-tuned with only a few additional training examples. We demonstrate that this simple strategy is robust to changes in the label space. Furthermore, our results show that learning a non-Euclidean metric can improve performance in the low data regime, suggesting that further work on metric spaces may benefit low-resource research.
翻译:传统文本分类系统仅限于预测固定标签。 但是, 在许多真实世界的应用中, 标签集经常变化。 例如, 在意图分类中, 可能随着时间推移而增加新的意图, 而其他的则被删除。 我们提议用一个有知识的、 具有语义意义的计量空间来取代传统的固定规模产出层, 以解决动态文本分类问题。 在这里, 文本输入之间的距离被优化, 以便在重叠的标签组中进行近邻分类 。 修改标签集并不涉及删除参数, 而是简单地在计量空间中添加或删除支持点 。 然后, 所学到的衡量尺度可以用其他几个培训实例进行微调。 我们证明这一简单战略对于标签空间的改变是强有力的。 此外, 我们的结果显示, 学习非欧洲语言的参数可以改善低数据系统的性能, 表明在计量空间上进一步的工作可能有利于低资源研究 。