No abstract

We applied Conditional Random Fields (CRFs) to the tasks of Amharic word segmentation and POS tagging using a small annotated corpus of 1000 words. Given the size of the data and the large number of unknown words in the test corpus (80%), an accuracy of 84% for Amharic word segmentation and 74% for POS tagging is encouraging, indicating the applicability of CRFs for a morphologically complex language like Amharic.

We present the results of feature engineering and post-processing experiments conducted on a temporal expression recognition task. The former explores the use of different kinds of tagging schemes and of exploiting a list of core temporal expressions during training. The latter is concerned with the use of this list for postprocessing the output of a system based on conditional random fields.We find that the incorporation of knowledge sources both for training and postprocessing improves recall, while the use of extended tagging schemes may help to offset the (mildly) negative impact on precision. Each of these approaches addresses a different aspect of the overall recognition performance. Taken separately, the impact on the overall performance is low, but by combining the approaches we achieve both high precision and high recall scores.

No abstract

No abstract