arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.06555cs.CLcs.AI
收藏

语义向量组合应该是显式的吗?它可以是线性的吗?

Should Semantic Vector Composition be Explicit? Can it be Linear?

LivePerson Inc.(LivePerson公司);University of Washington(华盛顿大学)

Dominic Widdows, Kristen Howell, Trevor Cohen

摘要:

向量表示已经成为语义语言建模的核心元素,导致包括量子理论在内的许多领域的数学重叠。组合性是这种表示的核心目标:给定“湿”和“鱼”的表示,“湿鱼”的概念应该如何表示?本立场文件从两个角度审视这一问题。第一个考虑的问题是,一个明确的数学表示是否可以成功地只使用工具从线性代数,或是否需要其他数学工具。第二个考虑语义向量组合是否应该明确地用数学描述,或者它是否可以是训练神经网络的模型内部副作用。第三个也是更新的问题是,组合模型是否可以在量子计算机上实现。考虑到量子力学的基本线性性质,我们认为这些问题是相关的,并且这项调查可能有助于突出未来量子实现的候选操作。

英文摘要:

Vector representations have become a central element in semantic language modelling, leading to mathematical overlaps with many fields including quantum theory. Compositionality is a core goal for such representations: given representations for 'wet' and 'fish', how should the concept 'wet fish' be represented? This position paper surveys this question from two points of view. The first considers the question of whether an explicit mathematical representation can be successful using only tools from within linear algebra, or whether other mathematical tools are needed. The second considers whether semantic vector composition should be explicitly described mathematically, or whether it can be a model-internal side-effect of training a neural network. A third and newer question is whether a compositional model can be implemented on a quantum computer. Given the fundamentally linear nature of quantum mechanics, we propose that these questions are related, and that this survey may help to highlight candidate operations for future quantum implementation.

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。

↑