Kateřina Rysová

Incorporating Coreference to Automatic Evaluation of Coherence in Essays

The paper contributes to the task of automated evaluation of surface coherence. It introduces a coreference-related extension to the EVALD applications, which aim at evaluating essays produced by native and non-native students learning Czech. Having successfully employed the coreference resolver and coreference-related features, our system outperforms the original EVALD approaches by up to 8% points. The paper also introduces a dataset for non-native speakers’ evaluation, which was collected from multiple corpora and the parts with missing annotation of coherence grade were manually judged. The resulting corpora contains sufficient number of examples for each of the grading levels.

Analyzing Text Coherence via Multiple Annotation in the Prague Dependency Treebank

Corpus-based research demonstrates an existence of a mutual interaction of bridging anaphoric relations in the text and sentence information structure. The research is carried out on large corpus data of the Prague Dependency Treebank 3.0 that contains almost 50 thousand sentences with manual annotation of both sentence information structure and bridging anaphora. We investigate in which way the bridging anaphora relations interconnect contextually bound and non-bound sentence items and how such types of connections contribute to the text coherence.