One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words
One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words
复制标题
DOI：
--
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Prafulla Kumar Choubey;Ruihong Huang
中科院分区：
文献类型：
--
作者：
Prafulla Kumar Choubey;Ruihong Huang
大多数有监督的词义消歧(WSD)系统通过利用标记数据来构建特定于单词的分类器。然而，当使用特定于单词的分类器时，注释的稀疏性导致对较不频繁出现的单词的语义消歧性能较差。为了解决数据稀疏的问题，我们建议学习一个单一的模型，该模型可以导出意义表示，同时通过使用语义注释数据和词汇资源来加强单词实例与其正确意义之间的一致性。该模型在单词之间共享，允许利用单词之间的意义相关性，因此有助于将常见的歧义消除规则从注释丰富的单词转移到注释稀少的单词。在基准数据集上的实验评估表明，在使用手套、Elmo和Bert词嵌入时，所提出的共享模型的F1-Score性能分别比基于分类器的模型高1.7%、2.5%和3.8%。
Most supervised word sense disambiguation (WSD) systems build word-specific classifiers by leveraging labeled data. However, when using word-specific classifiers, the sparseness of annotations leads to inferior sense disambiguation performance on less frequently seen words. To combat data sparsity, we propose to learn a single model that derives sense representations and meanwhile enforces congruence between a word instance and its right sense by using both sense-annotated data and lexical resources. The model is shared across words that allows utilizing sense correlations across words, and therefore helps to transfer common disambiguation rules from annotation-rich words to annotation-lean words. Empirical evaluation on benchmark datasets shows that the proposed shared model outperforms the equivalent classifier-based models by 1.7%, 2.5% and 3.8% in F1-score when using GloVe, ELMo and BERT word embeddings respectively.