Sentence retrieval for abstracts of randomized controlled trials

Table 7 Four Way Sentence Classification Results on Manually Annotated Abstracts

Sentence classification using CRFs into four rhetorical roles on manually annotated data set. The CRF model was trained on 13.6 k set of structured abstracts. Precision (P), Recall (R) and F-score (F) are reported for each label over the entire data set (318), the structured subset (211) and unstructured subset (107).

ISSN: 1472-6947