围攻下的上位词：基于语言动机的上位词检测
Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection
摘要：
上位关系在自然语言处理中的重要作用促使了许多自动识别这种关系的方法的发展，其中大多数依赖于词的分布。我们调查了大量的这种无监督的措施，使用几个不同的上下文类型和特征权重的分布式语义模型。我们分析了不同方法的性能，根据他们的语言动机。与最先进的监督方法的比较表明，虽然监督方法通常优于无监督方法，但前者对训练实例的分布敏感，损害了它们的可靠性。无监督度量基于一般的语言学假设，不依赖于训练数据，具有更强的鲁棒性，因此仍然是上位词检测的有用武器。
英文摘要：
The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution. We investigate an extensive number of such unsupervised measures, using several distributional semantic models that differ by context type and feature weighting. We analyze the performance of the different methods based on their linguistic motivation. Comparison to the state-of-the-art supervised methods shows that while supervised methods generally outperform the unsupervised ones, the former are sensitive to the distribution of training instances, hurting their reliability. Being based on general linguistic hypotheses and independent from training data, unsupervised measures are more robust, and therefore are still useful artillery for hypernymy detection.
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。
