[论文解读] Word sense disambiguation via bipartite representation of complex networks.

Edilson A. Corrêa, Alneu de Andrade Lopes+1 more|arXiv (Cornell University)|Jun 25, 2016

Topic Modeling参考文献 28被引用 36

一句话总结

本文提出了一种双部网络模型，将目标（歧义）词和特征（上下文）词均表示为网络中的节点，显式利用其语义关系进行词义消歧。通过构建一种结构，使基于主题特征的词义判别直接在拓扑结构上进行，该方法实现了优越的性能——在某些情况下优于支持向量机，尤其在小规模训练数据集上表现更佳。

ABSTRACT

In recent years, concepts and methods of complex networks have been employed to tackle the word sense disambiguation (WSD) task by representing words as nodes, which are connected if they are semantically similar. Despite the increasingly number of studies carried out with such models, most of them use networks just to represent the data, while the pattern recognition performed on the attribute space is performed using traditional learning techniques. In other words, the structural relationship between words have not been explicitly used in the pattern recognition process. In addition, only a few investigations have probed the suitability of representations based on bipartite networks and graphs (bigraphs) for the problem, as many approaches consider all possible links between words. In this context, we assess the relevance of a bipartite network model representing both feature words (i.e. the words characterizing the context) and target (ambiguous) words to solve ambiguities in written texts. Here, we focus on the semantical relationships between these two type of words, disregarding the relationships between feature words. In special, the proposed method not only serves to represent texts as graphs, but also constructs a structure on which the discrimination of senses is accomplished. Our results revealed that the proposed learning algorithm in such bipartite networks provides excellent results mostly when topical features are employed to characterize the context. Surprisingly, our method even outperformed the support vector machine algorithm in particular cases, with the advantage of being robust even if a small training dataset is available. Taken together, the results obtained here show that the proposed representation/classification method might be useful to improve the semantical characterization of written texts.

研究动机与目标

• 为解决传统词义消歧方法仅将复杂网络用于数据表示，而未显式用于模式识别的局限性。
• 探究双部网络表示在建模歧义词与其上下文词之间语义关系方面的有效性。
• 开发一种学习算法，直接在双部网络的结构特性上执行词义判别。
• 评估主题特征是否能提升所提出的基于网络的词义消歧框架的性能。

提出的方法

• 该方法构建一个双部网络，其中一组节点表示歧义（目标）词，另一组节点表示上下文中的特征词。
• 语义关系仅在目标词与特征词之间建立，排除特征词之间的直接连接，以简化结构并聚焦于上下文到目标的关联。
• 以网络结构作为分类的主要依据，通过拓扑分析而非传统属性空间上的机器学习进行词义判别。
• 使用主题特征来表征上下文，增强模型捕捉相关语义线索的能力。
• 学习算法利用网络的连通性模式，为歧义词分配最可能的词义。
• 通过标准词义消歧基准数据集对方法进行评估，并与支持向量机及其他基线方法进行性能比较。

实验结果

研究问题

• RQ1 双部网络表示能否有效建模歧义词与其上下文特征之间的语义关系，以实现词义消歧？
• RQ2 所提出的基于网络的方法在词义消歧任务中与传统机器学习方法（如支持向量机）相比表现如何？
• RQ3 使用主题特征在多大程度上提升了双部网络模型中词义判别的准确性？
• RQ4 当使用小规模数据集进行训练时，所提出的方法是否仍能保持稳健的性能？

主要发现

• 在使用主题特征表征上下文的情况下，所提出的方法在特定情形下优于支持向量机。
• 即使训练数据有限，该方法仍表现出稳健的性能，表明其具有强大的泛化能力。
• 使用主题特征显著增强了模型解析词义歧义的能力。
• 双部网络结构通过显式建模目标词与特征词之间的关系，实现了有效的词义判别，而无需依赖传统的属性空间学习。