Statistical Principle-based Approach for Gene and Protein Related Object Recognition

@inproceedings{Lai2017StatisticalPA,
  title={Statistical Principle-based Approach for Gene and Protein Related Object Recognition},
  author={Po-Ting Lai and Ming-Siang Huang and Chu-Hsien Su and Richard Tzong-Han Tsai and Wen-Lian Hsu},
  year={2017}
}
We introduce a Statistical Principle-based Approach (SPBA) for named entity recognition (NER). SPBA is a pattern-based approach. It uses patterns to represent protein names, and uses the semantic labels to map sentence into labeled sentence. NER is then formulated as aligning labeled sentence with patterns. The weights of insertion/deletion/match are learned through logistic regression model in our refactored JNLPBA corpus. We participated in BioCreative V.5 Gene and Protein Related Object… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-8 of 8 references

ExPASy: SIB bioinformatics resource portal

Nucleic Acids Research • 2012
View 2 Excerpts

Multistage gene normalization for fulltext articles with context-based species filtering for dynamic dictionary entry selection

Tsai, R.T.-H., Lai, P.-T.
BMC Bioinformatics 12 Suppl 8, • 2011
View 1 Excerpt

Introduction to the bio-entity recognition task at JNLPBA

Kim, J.-D., +3 authors N. Collier
Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications, pp. 70-75. Association for Computational Linguistics, Geneva, Switzerland • 2004
View 1 Excerpt

Similar Papers

Loading similar papers…