Taskar, B. et al, NIPS 2003

Citation

B. Taskar, C. Guestrin, D. Koller, 2003. Max-Margin Markov Networks. NIPS.

Online version

Link

Summary

This paper presents an Maximum Margin Markov Network method that combines advantages of kernel-based methods and probabilistic classifiers.

Brief description of the method

The method is a pretty simple extension of a standard active learning method. The following figure describes the general active learning framework.

The authors refer the usual active learning mode as fully supervised active learning (FuSAL). The utility function used in FuSAL is

$U_{\mathbf {\lambda } }(\mathbf {x} )=1-P_{\mathbf {\lambda } }(\mathbf {y} ^{*}\vert \mathbf {x} )$

which makes the sampling method as an uncertainty sampling method.

The problem of FuSAL in the sequence labeling scenario is that an example that has a high utility can still have parts of it that the current model can label very well, thus not contribute much to the utility of the whole. Therefore, it means we can leave some of the labels that the current model labeled if the confidence on that particular token is high enough. The authors name this as semi-supervised active learning (SeSAL). It combines the benefits of Active Learning and Bootstrapping, which are labeling only examples with high utility and minimizing annotation effort by partially labeling examples where the model is confident about the prediction. In pseudocode, the following shows the steps that are added to the FuSAL:

3.1 For each example $p_{i}\quad$

3.1.1 For each token $x_{j}\quad$ and the most likely label $y_{j}^{*}\quad$

3.1.1.1 Compute the model's confidence in the predicted label $C_{\mathbf {\lambda } }(y_{j}^{*})=P_{\mathbf {\lambda } }(y_{j}=y_{j}^{*}\vert \mathbf {x} )$

3.1.2 Remove all labels whose confidence is lower than some threshold $t$

Since there is a bootstrapping element in the method, the size of the seed set is also important. Therefore the authors suggest running FuSAL several iterations before switching to SeSAL.

Experimental Result

The authors tested this method on MUC-7 and the oncology part of PennBioIE corpus. The base learner used for the experiment is a linear-chain Conditional Random Fields. Features used are orthographical features (regexp patterns), lexical and morphological features (prefix, suffix, lemmatized tokens), and contextual features (features of neighbor tokens). In terms of the number of tokens that had to be labled to reach the maximal F-score, SeSAL could save about 60% over FuSAL, and 80% over random sampling. Having high confidence was also important because it could save the model from making errors in the early stages.

Related papers

• Muslea, Minton and Knoblock, ICML 2002
• McCallum and Ngiam, ICML 98

Comment

If you're further interested in active learning for NLP, you might want to see Burr Settles' review of active learning: http://active-learning.net/ --Brendan 22:51, 13 October 2011 (UTC)