Paper: Recall-Oriented Learning of Named Entities in Arabic Wikipedia

ACL ID E12-1017
Title Recall-Oriented Learning of Named Entities in Arabic Wikipedia
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

We consider the problem of NER in Arabic Wikipedia, a semisupervised domain adap- tation setting for which we have no labeled training data in the target domain. To fa- cilitate evaluation, we obtain annotations for articles in four topical groups, allow- ing annotators to identify domain-specific entity types in addition to standard cate- gories. Standard supervised learning on newswire text leads to poor target-domain recall. We train a sequence model and show that a simple modification to the online learner?a loss function encouraging it to ?arrogantly? favor recall over precision? substantially improves recall and F1. We then adapt our model with self-training on unlabeled target-domain data; enforc- ing the same recall-oriented bias in the self- training stage yields marginal gains.1