English notes for KG

1. For example, if we want the model to acquire the knowledge of
   “Paracetamol can treat cold”, a large number of cooccurrences of
   ”Paracetamol” and ”cold” are required in the pre-training
   corpus. Instead of this strategy, what else can we do to make
   the model a domain expert? The knowledge graph (KG), which was
   called ontology in early research, serves as a good solution。
   例如，如果我们想让模型获得“扑热息痛可以治疗感冒”的知识，那么在训练前的语料 库中就需要大量的“扑热息痛”和“感冒”同时出现。除了这个策略，我们还能做些什么让模型成为领域专家呢？知识图（KG）在早期的研究中被称为本体论，是一种很好的解决方案。

2. As shown in Figure 1, the model architecture of K-BERT consists of four modules, i.e., knowledge layer, embeddinglayer, seeing layer and mask-transformer.
   如图1所示，××模型体系结构由××××层、××××层、××××层和××××四个模块组成

3. To some degree
   在某种程度上

4. However, there are two challenges lies in the road of this knowledge integration: (1) Heterogeneous Embedding Space (HES): In general, the embedding vectors of words in text and entities in KG are obtained in separate ways, making their vector-space inconsistent; (2) Knowledge Noise (KN): Too much knowledge incorporation may divert the sentence from its correct meaning. To overcome these challenges, this paper propose a Knowledge-enabled Bidirectional Encoder Representation from Transformers (K-BERT).
   然而，在×××××的道路上有两个挑战：（1）×××（2）××××××