论文标题
Deep Daxes：通过学习偏见和神经网络中的务实策略产生相互排他性
Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks
论文作者
论文摘要
儿童倾向于将新颖单词与新颖的指称人联系起来，以反映对相互排他性的偏见。这种趋势可能是有利的，因为（1）对缺乏标签的单身参考人以及（2）词汇采集的组织原则。本文调查了在哪些情况下，跨性化神经模型可以表现出对儿童的类似行为，重点是这两种可能性及其相互作用。为此，我们在符号数据上评估了神经网络，并首先在大规模图像数据上评估了神经网络。我们发现，只要他们在词汇含义的竞争中列出一句话，学习和选择中的限制都可以培养共同的排他性。对于计算模型，这些发现阐明了可用选项的作用，以在相互排他性有利的任务中提高性能。对于认知研究，它们强调了单词学习，参考选择机制和不同复杂性刺激的结构之间的潜在相互作用：符号和视觉。
Children's tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency may be advantageous both as (1) an ad-hoc referent selection heuristic to single out referents lacking a label and as (2) an organizing principle of lexical acquisition. This paper investigates under which circumstances cross-situational neural models can come to exhibit analogous behavior to children, focusing on these two possibilities and their interaction. To this end, we evaluate neural networks' on both symbolic data and, as a first, on large-scale image data. We find that constraints in both learning and selection can foster mutual exclusivity, as long as they put words in competition for lexical meaning. For computational models, these findings clarify the role of available options for better performance in tasks where mutual exclusivity is advantageous. For cognitive research, they highlight latent interactions between word learning, referent selection mechanisms, and the structure of stimuli of varying complexity: symbolic and visual.
