Experimental Setup | Evaluation Measures Following standard practice, we use Unlabeled Attachment Score ( UAS ) as the evaluation metric in all our experiments. |
Experimental Setup | We report UAS excluding punctuation on CoNLL datasets, following Martins et al. |
Experimental Setup | For the CATiB dataset, we report UAS including punctuation in order to be consistent with the published results in the 2013 SPMRL shared task (Seddah et al., 2013). |
Results | Moreover, our model also outperforms the 88.80% average UAS reported in Martins et al. |
Results | With these features our model achieves an average UAS 89.28%. |
Results | UAS POS Acc. |
Experiments | Evaluation metrics: we evaluate our parsing systems by using the standard metrics for dependency parsing: Labeled Attachment Score (LAS) and Unlabeled Attachment Score ( UAS ), computed using all tokens including punctuation. |
Experiments | In the “labeled representation” evaluation, the UAS provides a measure of syntactic attachments for sequences of words, independently of the (regular) MWE status of subse-quences. |
Experiments | The UAS for labeled representation will be maximal, whereas for the flat representation, the last two tokens will count as incorrect for UAS . |
Abstract | We also obtain the best published UAS results on 5 languages.1 |
Experimental Setup | As the evaluation measure, we use unlabeled attachment scores ( UAS ) excluding punctuation. |
Results | Our model also achieves the best UAS on 5 languages. |
Results | Figure 1 shows the average UAS on CoNLL test datasets after each training epoch. |
Results | Figure 1: Average UAS on CoNLL testsets after different epochs. |
Experiments and Analysis | We measure parsing performance using the standard unlabeled attachment score ( UAS ), excluding punctuation marks. |
Experiments and Analysis | Table 4: UAS comparison on English test data. |
Experiments and Analysis | UAS Li et al. |
Domain Adaptation | Specifically, we measure the similarity, sim(ug), 103), between the source domain distributions of ua) and w, and select the top 7“ similar neighbours ua ) for each word 21) as additional features for 212. |
Domain Adaptation | The value of a neighbour ua ) selected as a distributional feature is set to its similarity score sim(ug), 103). |
Domain Adaptation | At test time, for each word 21) that appears in a target domain test sentence, we measure the similarity, sim(Mug), 107), and select the most similar 7“ words ua ) in the source domain labeled sentences as the distributional features for 212, with their values set to sim(Mug), wT). |
Data and Tools | Table 3: UAS for two versions of our approach, together with baseline and oracle systems on Google Universal Treebanks version 1.0. |
Data and Tools | Table 4: UAS for two versions of our approach, together with baseline and oracle systems on Google Universal Treebanks version 2.0. |
Experiments | Parsing accuracy is measured with unlabeled attachment score ( UAS ): the percentage of words with the correct head. |
Experiments | Moreover, our approach considerably bridges the gap to fully supervised dependency parsers, whose average UAS is 84.67%. |
Experiments | Table 5 illustrates the UAS of our approach trained on different amounts of parallel data, together with the results of the projected transfer parser re-implemented by us (PTPT). |