HyperBox:一种使用盒嵌入的有监督上位词发现方法
HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings
AI总结:
本文提出基于盒嵌入的有监督模型 HyperBox,用于上位词发现,在 SemEval 2018 数据集的医学和音乐领域上多数指标优于现有方法,并展现出良好的少样本泛化能力。
摘要:
上位关系在许多人工智能任务(如分类体系学习、本体学习等)中发挥着基础性作用。这推动了大量自动识别方法的发展,用于提取这种关系,其中大多数方法依赖于词分布。我们提出了一种新颖的模型 HyperBox,用于学习盒嵌入以进行上位词发现。给定一个输入词项,HyperBox 从目标语料库中检索其合适的上位词。针对该任务,我们使用了为 SemEval 2018 上位词发现共享任务发布的数据集。我们比较了模型在两个特定知识领域(医学和音乐)上的性能。实验表明,我们的模型在大多数评估指标上优于现有方法。此外,我们的模型仅使用少量训练数据就能对未见过的上位关系词对进行良好的泛化。
英文摘要:
Hypernymy plays a fundamental role in many AI tasks like taxonomy learning, ontology learning, etc. This has motivated the development of many automatic identification methods for extracting this relation, most of which rely on word distribution. We present a novel model HyperBox to learn box embeddings for hypernym discovery. Given an input term, HyperBox retrieves its suitable hypernym from a target corpus. For this task, we use the dataset published for SemEval 2018 Shared Task on Hypernym Discovery. We compare the performance of our model on two specific domains of knowledge: medical and music. Experimentally, we show that our model outperforms existing methods on the majority of the evaluation metrics. Moreover, our model generalize well over unseen hypernymy pairs using only a small set of training data.
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。