While MUC has a deficiency in that putting everything into a single cluster will artificially inflate the score, parameters on our model are set so that the model uses the same number of clusters as the baseline system .

While it would be possible to artificially inflate the score by putting everything into a single cluster, the parameters on our model and the likelihood objective are such that the model prefers to use all available clusters, the same number as the baseline system .

While our system does suffer on precision in comparison to the baseline system , the recall gains far outweigh this loss, for a total error reduction of 20% on the MUC measure.

When training on different sizes of data, our semi-supervised approach consistently outperformed a state-of-the-art supervised baseline system .

Nonetheless, we believe our baseline system has achieved very competitive performance.

We now describe a supervised baseline system with a very large set of features and its learning strategy.

Section 4 describes in detail a state-of-the-art supervised baseline system .

Extensive experiments involving large-scale English-to-Japanese translation revealed a significant improvement of 1.8 points in BLEU score, as compared with a strong forest-to-string baseline system .

Extensive experiments on large-scale English-to-Japanese translation resulted in a significant improvement in BLEU score of 1.8 points (p < 0.01), as compared with our implementation of a strong forest-to-string baseline system (Mi et al., 2008; Mi and Huang, 2008).

We implemented the forest-to-string decoder described in (Mi et al., 2008) that makes use of forest-based translation rules (Mi and Huang, 2008) as the baseline system for translating English HPSG forests into Japanese sentences.

Joshua V1.3 (Li et al., 2009), which is a freely available decoder for hierarchical phrase-based SMT (Chiang, 2005), is used as an external baseline system for comparison.

For our word-based Baseline system , we trained a word-based model using the same Moses system with identical settings.

For evaluation against segmented translation systems in segmented forms before word reconstruction, we also segmented the baseline system’s word-based output.

So, we ran the word-based baseline system , the segmented model (Unsup L—match), and the prediction model (CRF—LM) outputs, along with the reference translation through the supervised morphological analyzer Omorfi (Piri—nen and Listenmaa, 2007).