Bootstrapping Coreference Classifiers with Multiple Machine Learning Algorithms
By Vincent Ng, Claire Cardie. 2003
51 citations recorded by the source corpus.
Successful application of multi-view co-training algorithms relies on the ability to factor the available features into views that are compatible and uncorrelated. This can potentially preclude their use on problems such as coreference resolution that lack an obvious feature split. To bootstrap coreference classifiers, we propose and evaluate a single-view weakly supervised algorithm that relies on two different learning algorithms in lieu of the two different views required by co-training. In addition, we investigate a method for ranking unlabeled instances to be fed back into the bootstrapping loop as labeled data, aiming to alleviate the problem of performance deterioration that is commonly observed in the course of bootstrapping.
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
- Hinrich Schütze
- Yang Trista Cao
- Hal Daumé Iii
- Hans Kamp
- Michael Schiehlen
- Hamidreza Kobdani
- Mohit Bansal
- Timo Schick
In Natural Language Processing
- Yang Trista Cao
- Hal Daumé Iii
- Hinrich Schütze
- Hans Kamp
- Michael Schiehlen
- Hamidreza Kobdani
- Mohit Bansal
- Timo Schick
Citations in the corpus
- Toward Gender-Inclusive Coreference Resolution (2019, methodology): “Considering the approaches used in dominant papers, the active learning ∨ ∧ algorithms used are not statistically unbiased [Guha et al. 2015; Laws et al. 2012; Miller et al. 2012; Ng and Cardie 2003; Sachan et al. 2015].”
- Bootstrapping coreference resolution using word associations (2011, methodology): “A key difference to the work by M¨uller et al. (2002) and Ng and Cardie (2003) is that we do not use any human-labeled coreference pairs.”
- Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle* (2021, methodology): “Considering the approaches used in dominant papers, the active learning algorithms used are not statistically unbiased (Ng and Cardie 2003; Laws, Heimerl, and Schütze 2012; Miller, Dligach, and Savova 2012; Sachan, Hovy, and Xing 2015; Guha et al. 2015).”