A promising approach for knowledge-based Word Sense Disambiguation (WSD) is to select the sense whose contextualized embeddings computed for its definition sentence are closest to those computed for a target word in a given sentence. This approach relies on the similarity of the \textit{sense} and \textit{context} embeddings computed by a pre-trained language model. We propose a semantic specialization for WSD where contextualized embeddings are adapted to the WSD task using solely lexical knowledge. The key idea is, for a given sense, to bring semantically related senses and contexts closer and send different/unrelated senses farther away. We realize this idea as the joint optimization of the Attract-Repel objective for sense pairs and the self-training objective for context-sense pairs while controlling deviations from the original embeddings. The proposed method outperformed previous studies that adapt contextualized embeddings. It achieved state-of-the-art performance on knowledge-based WSD when combined with the reranking heuristic that uses the sense inventory. We found that the similarity characteristics of specialized embeddings conform to the key idea. We also found that the (dis)similarity of embeddings between the related/different/unrelated senses correlates well with the performance of WSD.

翻译：基于知识的词义消歧（WSD）的一种有前景的方法是：选择其定义句计算得到的上下文嵌入与给定句子中目标词计算得到的嵌入最接近的义项。该方法依赖于预训练语言模型计算的**义项**和**上下文**嵌入的相似性。我们提出一种针对WSD的语义特化方法，仅利用词汇知识将上下文嵌入适配到WSD任务中。核心思想是：对于给定的义项，拉近语义相关的义项和上下文，同时推远不同/无关的义项。我们通过联合优化义项对的吸引-排斥目标和上下文-义项对的自训练目标来实现这一思想，同时控制与原始嵌入的偏离程度。所提出的方法优于先前适配上下文嵌入的研究。当结合使用义项清单的重排序启发式方法时，该方法在基于知识的WSD上达到了最先进的性能。我们发现，特化嵌入的相似性特征符合核心思想。我们还发现，相关/不同/无关义项之间嵌入的（不）相似性与WSD性能密切相关。