Name Tagging with Word Clusters and Discriminative Training

We present a technique for augmenting annotated training data with hierarchical word clusters that are automatically derived from a large unannotated corpus. Cluster membership is encoded in features that are incorporated in a discriminatively trained tagging model. Active learning is used to select training examples. We evaluate the technique for named-entity tagging. Compared with a state-of-the-art HMM-based name finder, the presented technique requires only 13% as much annotated data to achieve the same level of performance. Given a large annotated training set of 1,000,000 words, the technique achieves a 25% reduction in error over the state-of-the-art HMM trained on the same material.

• Type: Conference
• Year: 2004
• Where: NAACL
• Authors: Scott Miller, Jethran Guinness, Alex Zamanian
• Keywords: Annotated Training, Annotated Training Data, Large Unannotated Corpus, NAACL 2004, NAACL 2007