Global Attention for Name Tagging
This addresses name tagging in NLP for languages like Dutch, German, and Spanish, showing incremental improvements over existing methods.
The paper tackles the problem of name tagging when local context is ambiguous or limited by introducing a framework that uses local, document-level, and corpus-level contextual information with global attentions and gating mechanisms. It achieves state-of-the-art results on CoNLL-2002 and CoNLL-2003 datasets for Dutch, German, and Spanish.
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-level, and corpus-level contextual information. We retrieve document-level context from other sentences within the same document and corpus-level context from sentences in other topically related documents. We propose a model that learns to incorporate document-level and corpus-level contextual information alongside local contextual information via global attentions, which dynamically weight their respective contextual information, and gating mechanisms, which determine the influence of this information. Extensive experiments on benchmark datasets show the effectiveness of our approach, which achieves state-of-the-art results for Dutch, German, and Spanish on the CoNLL-2002 and CoNLL-2003 datasets.