Syntax-based Semi-Supervised Named Entity Tagging
By Behrang Mohit, Rebecca Hwa. 2005
28 citations recorded by the source corpus.
We report an empirical study on the role of syntactic features in building a semi-supervised named entity (NE) tagger. Our study addresses two questions: What types of syntactic features are suitable for extracting potential NEs to train a classifier in a semi-supervised setting? How good is the resulting NE classifier on testing instances dissimilar from its training data? Our study shows that constituency and dependency parsing constraints are both suitable features to extract NEs and train the classifier. Moreover, the classifier showed significant accuracy improvement when constituency features are combined with new dependency feature. Furthermore, the degradation in accuracy on unfamiliar test cases is low, suggesting that the trained classifier generalizes well.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Matthew E. Peters
- Chandra Bhagavatula
- Bridger Waleed Ammar
- Russell Power
- Hannaneh Hajishirzi
- Noah A. Smith
- Sebastian Ruder
- Yejin Choi
In Natural Language Processing
- Matthew E. Peters
- Chandra Bhagavatula
- Bridger Waleed Ammar
- Russell Power
- Hannaneh Hajishirzi
- Yejin Choi
- Sebastian Ruder
- Jonathan Berant
Citations in the corpus
- Semi-supervised sequence tagging with bidirectional language models (2017, background): “…structured prediction problems include co-training (Blum and Mitchell, 1998; Pierce and Cardie, 2001), expectation maximization (Nigam et al., 2000; Mohit and Hwa, 2005), structural learning (Ando and Zhang, 2005) and maximum discriminant functions (Suzuki et al., 2007; Suzuki and Isozaki, 2008).”