In this work, we study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of contextualized representations. Instead of seeking alignments to existing well-defined annotations, we infer this latent network in a fully unsupervised way using a structured variational autoencoder. The induced states not only serve as anchors that mark the topology (neighbors and connectivity) of the representation manifold but also reveal the internal mechanism of encoding sentences. With the induced network, we: (1). decompose the representation space into a spectrum of latent states which encode fine-grained word meanings with lexical, morphological, syntactic and semantic information; (2). show state-state transitions encode rich phrase constructions and serve as the backbones of the latent space. Putting the two together, we show that sentences are represented as a traversal over the latent network where state-state transition chains encode syntactic templates and state-word emissions fill in the content. We demonstrate these insights with extensive experiments and visualizations.
翻译:在这项工作中,我们研究了背景嵌入层的展示空间,并深入了解了大型语言模型的隐藏地形。我们展示了存在一个潜在状态的网络,其中总结了背景表达面的语言特性。我们不寻求与现有定义清晰的注释保持一致,而是利用结构化的变异自动编码器,以一种完全不受监督的方式推断了这一潜在网络。被引致的各州不仅充当标出代表方的地形(邻居和连接)的锚,而且还暴露了编码句的内部机制。通过诱导的网络,我们:(1) 将代表空间分解成一个将细微区分的字义与词典、形态学、合成学和语义学信息编码起来的潜在状态状态的频谱;(2) 展示了将丰富的词组构造编码成丰富词组的状态转型,并充当了潜在空间的骨干。加在一起,我们证明这些句子代表着对潜在网络的曲折。我们用大量实验和视觉化的方式展示了这些洞察力和洞察力。