Word sense disambiguation is a process to correctly identify the meanings of words in a given context. Being important in many natural language processing applications, this process is crucial in automatically understanding natural language expressions. Herein, we propose a variation of a well-known unsupervised graph-based word sense disambiguation method that utilizes all possible semantic information from a used lexical resource to increase graph-semantic connectivity for identifying the intended meanings of words in a given context. If the words have multiple potential meanings (senses) based on context, the proposed method builds an expanded graph representing most relevant semantic information of the words to be disambiguated. Nodes in the graph correspond to the context expansion set, which contains all associated information of each possible meaning of the word (word sense), and edges represent the semantic similarity between the expanded sets (nodes). Simultaneously, actual meaning is assigned to each target word using a locate graph centrality measure, which provides the degree of importance between graph nodes. Unlike most existing graph-based word sense disambiguation methods, wherein semantic relations (edges) between nodes are measured at the word level, the proposed method measures graph node semantic relations at the sentence level by expanding the words’ context, which contains all associated information for each possible word sense. Consequently, the proposed method can capture a higher degree of semantic information than existing approaches, thereby increasing semantic connectivity through a graph’s edges. Empirical results on benchmark datasets demonstrate that the proposed method outperforms all compared state-of-the-art graph-based word sense disambiguation approaches reported herein. We also report results obtained by applying the proposed method to a sentiment analysis task. These results demonstrate that the proposed method can determine the overall sentiment orientation of a given textual context.

词义歧义消除是在给定上下文中正确识别词义的过程。在许多自然语言处理应用程序中很重要，此过程对于自动理解自然语言表达至关重要。在本文中，我们提出了一种众所周知的基于图的无监督词义消歧方法的变体，该方法利用来自使用的词汇资源的所有可能的语义信息来增加图语义连接性，以识别给定上下文中词的预期含义。如果单词具有基于上下文的多种潜在含义（感觉），则所提出的方法将构建一个展开图，该图表示待消除单词的最相关语义信息。图中的节点对应于上下文扩展集，其中包含与该单词的每种可能含义（单词含义）相关的所有信息，并且边缘表示扩展集（节点）之间的语义相似性。同时，使用定位图中心度度量将实际含义分配给每个目标词，从而提供图节点之间的重要程度。与大多数现有的基于图的词义消歧方法不同，在消歧方法中，节点之间的语义关系（边缘）是在在单词级别，该方法通过扩展单词的上下文来测量句子级别的图节点语义关系，该上下文包含每种可能的单词含义的所有相关信息。因此，与现有方法相比，所提出的方法可以捕获更高程度的语义信息，从而通过图的边缘增加语义连通性。基准数据集上的经验结果表明，所提出的方法优于本文报告的所有比较的基于现有技术的最先进的基于图的词义消歧方法。我们还将报告通过将建议的方法应用于情感分析任务而获得的结果。这些结果表明，所提出的方法可以确定给定文本上下文的总体情感取向。