Indeed, the difference between our best results and those of Elsner and Charniak are not statistically significant.

Table 3 finally shows that syntactic information improves the performance of our system (yet not significantly) and gives the best results (PACC).

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).

These extensions led to the best results reported so far for the sentence ordering task.

We compared our best results with the participating systems of the task.

As shown in the table, our best results outperform all of the systems and the MFS baseline.

It maps our best results in the distribution of all the 20 unsupervised/knowledge-based participating systems.

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.

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.

However, making use of all these layers of metadata together gives substantial further improvements, reaching the best result with Com-binedA,3,T.