@techreport{oai:ipsj.ixsq.nii.ac.jp:00047714, author = {Yue, Wang and Kazuhiro, Yoshida and Jin-DongKim and Rune, S?tre and Jun'ichi, Tsujii and Yue, Wang and Kazuhiro, Yoshida and Jin-Dong, Kim and Rune, Satre and Jun'ichi, Tsujii}, issue = {46(2008-NL-185)}, month = {May}, note = {The use of human-annotated corpora is popular in developing language processing systems. For bio-text mining for example there are several well-known corpora with protein mention annotations. Because of the different conventions adopted by these corpora one problem that is well recognized but yet less addressed is brought about; the problem is the heterogeneity of the corpora. The problem weakens the protein annotation consistency. In this work we seek a way of removing or relaxing the heterogeneity of annotations by identifying and removing the specific difference between the annotations. Our results show that our effort to remove several disagreements between the corpora annotation is successful in reducing the performance degradation caused by heterogeneity and incompatibility., The use of human-annotated corpora is popular in developing language processing systems. For bio-text mining, for example, there are several well-known corpora with protein mention annotations. Because of the different conventions adopted by these corpora, one problem that is well recognized, but yet less addressed is brought about; the problem is the heterogeneity of the corpora. The problem weakens the protein annotation consistency. In this work, we seek a way of removing or relaxing the heterogeneity of annotations by identifying and removing the specific difference between the annotations. Our results show that our effort to remove several disagreements between the corpora annotation is successful in reducing the performance degradation caused by heterogeneity and incompatibility.}, title = {Raising the Compatibility of Heterogeneous Annotations : A Case Study on Protein Mention Recognition}, year = {2008} }