Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model
Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model
复制标题
用专业化张量模型区分词汇语义关系
DOI：
10.18653/v1/n18-2029
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Ivan Vulic
中科院分区：
文献类型：
--
作者：
Goran Glavas;Ivan Vulic
我们提出了一种简单有效的前馈神经结构，用于区分词汇语义关系（同义词、反义词、上义和异名）。我们的专门化张量模型（STM）同时产生多个不同的输入分布词向量专门化，用于预测词对的词汇语义关系。STM在两个基准数据集上的性能优于更复杂的最先进的体系结构，并且在不同语言之间表现出稳定的性能。我们还表明，如果与双语分布空间相结合，该模型可以在不需要任何训练数据的情况下将词典语义关系的预测转移到资源贫乏的目标语言。
We present a simple and effective feed-forward neural architecture for discriminating between lexico-semantic relations (synonymy, antonymy, hypernymy, and meronymy). Our Specialization Tensor Model (STM) simultaneously produces multiple different specializations of input distributional word vectors, tailored for predicting lexico-semantic relations for word pairs. STM outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages. We also show that, if coupled with a bilingual distributional space, the proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data.