Structured Output Learning with Indirect Supervision.
ICML'10: Proceedings of the 27th International Conference on International Conference on Machine Learning(2010)
摘要
We present a novel approach for structure prediction that addresses the difficulty of obtaining labeled structures for training. We observe that structured output problems often have a companion learning problem of determining whether a given input possesses a good structure. For example, the companion problem for the part-of-speech (POS) tagging task asks whether a given sequence of words has a corresponding sequence of POS tags that is "legitimate". While obtaining direct supervision for structures is difficult and expensive, it is often very easy to obtain indirect supervision from the companion binary decision problem. In this paper, we develop a large margin framework that jointly learns from both direct and indirect forms of supervision. Our experiments exhibit the significant contribution of the easy-to-get indirect binary supervision on three important NLP structure learning problems.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络