Domain and Function: A Dual-Space Model of Semantic Relations and Compositions
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions
复制标题
DOI：
10.1613/jair.3640
复制
发表时间：
2012-01-01
影响因子：
5
通讯作者：
Turney, Peter D.
中科院分区：
文献类型：
--
作者：
Turney, Peter D.
给定木匠和木材之间以及泥瓦匠和石头之间的语义关系的适当表示（例如，向量空间模型中的向量），合适的算法应该能够识别出这些关系是高度相似的（木匠是木材，泥瓦匠是石头；关系是类似的）。同样，对于dog、house和kennel的表示，算法应该能够识别出dog和house （dog house）的语义组成与kennel （dog house和kennel是同义词）高度相似。认识关系和构成这两项任务似乎是紧密相连的。然而，到目前为止，关系的最佳模型与组合的最佳模型有很大的不同。在本文中，我们引入了一个统一这两个任务的双空间模型。该模型与以前最好的关系和组合模型的性能相匹配。双空间模型由测量域相似度的空间和测量函数相似度的空间组成。木匠和木头共享同一个领域，即木工领域。Mason和stone属于同一个领域，即砌筑领域。木匠和泥瓦匠都有同样的功能，工匠的功能。木材和石材具有相同的功能，材料的功能。在dog house的构图中，kennel与dog和house（宠物和建筑的领域）有一些重叠。犬舍的功能类似于房子的功能（庇护所的功能）。通过以各种方式组合域和函数相似性，我们可以对关系、组合和语义的其他方面进行建模。
Given appropriate representations of the semantic relations between carpenter and wood and between mason and stone (for example, vectors in a vector space model), a suitable algorithm should be able to recognize that these relations are highly similar (carpenter is to wood as mason is to stone; the relations are analogous). Likewise, with representations of dog, house, and kennel, an algorithm should be able to recognize that the semantic composition of dog and house, dog house, is highly similar to kennel (dog house and kennel are synonymous). It seems that these two tasks, recognizing relations and compositions, are closely connected. However, up to now, the best models for relations are significantly different from the best models for compositions. In this paper, we introduce a dual-space model that unifies these two tasks. This model matches the performance of the best previous models for relations and compositions. The dual-space model consists of a space for measuring domain similarity and a space for measuring function similarity. Carpenter and wood share the same domain, the domain of carpentry. Mason and stone share the same domain, the domain of masonry. Carpenter and mason share the same function, the function of artisans. Wood and stone share the same function, the function of materials. In the composition dog house, kennel has some domain overlap with both dog and house (the domains of pets and buildings). The function of kennel is similar to the function of house (the function of shelters). By combining domain and function similarities in various ways, we can model relations, compositions, and other aspects of semantics.