Experiments | Indeed, the difference between our best results and those of Elsner and Charniak are not statistically significant. |
Experiments | Table 3 finally shows that syntactic information improves the performance of our system (yet not significantly) and gives the best results (PACC). |
Experiments | The best results , that present a statistically significant improvement when compared to the random baseline, are obtained when distance information and the number of entities “shared” by two sentences are taken into account (PW). |
The Entity Grid Model | These extensions led to the best results reported so far for the sentence ordering task. |
Evaluation | We compared our best results with the participating systems of the task. |
Evaluation | As shown in the table, our best results outperform all of the systems and the MFS baseline. |
Evaluation | It maps our best results in the distribution of all the 20 unsupervised/knowledge-based participating systems. |
Multitask Quality Estimation 4.1 Experimental Setup | Including per-annotator noise to the pooled model provides a boost in performance, however the best results are obtained using the Combined kernel which brings the strengths of both the independent and pooled settings. |
Multitask Quality Estimation 4.1 Experimental Setup | The MTL model trained on 500 samples had an MAE of 0.7082 j: 0.0042, close to the best results from the full dataset in Table 2, despite using % as much data: here we use % as many training instances where each is singly (cf. |
Multitask Quality Estimation 4.1 Experimental Setup | However, making use of all these layers of metadata together gives substantial further improvements, reaching the best result with Com-binedA,3,T. |