1. Full name: Tran Mai Vu                                              2. Sex: Male

3. Date of birth:             25/08/1984                                            4. Place of birth: Thua Thien Hue           

5. Admission decision number: 3205/QĐ-SĐH     Dated 08/11/2010       

6. Changes in academic process:                      

(List the forms of change and corresponding times)

7. Official thesis title:    

8. Major:                                                                       9. Code:          

10. Supervisors:           

(Full name, academic title and degree)

11. Summary of the new findings of the thesis:  

Main achieved science results:

- Proposing the model for recognizing entities and their attributes simultaneously. This model allows using various features for enhancing the semantic characteristics and the model effectiveness. A dataset of 10.000 sentences was annotated with entities and their attributes. The results of proposed model reached 83.39 of F1.

- Developing a Vietnamese question answering system (QAS) which based on proposed model of recognizing entities and their attributes. Both steps of question analyzing and answering show the importance of NER in QAS. The results of QAS is positive, reached 65.5 of F1.

- Contributing to expanding biomedical entities structure frame, consisting and generalizing the definitions of related biomedical entities, such as disease, chemical, gene, organism, body part and phenotype.

- Proposing model to recognize phenotype and related entities, in which, phenotype is a semantically complex entity. The model reached positive results in all phenotype of our scheme.

- Giving the comparisons, judgments about problem of domain adaptive for biomedical NER, the results give future biomedical NER researches a general view to select data for training and evaluating.

- Improving the effectiveness of biomedical NER system by building the hybrid model which is the combining of several different NER methods. Thesis proposed 3 hybrid approaches and evaluated them. The results showed the effectiveness of the hybrid approach than single NER techniques that increase the model results 1.5% of F1.

12. Practical applicability, if any:           

13. Further research directions, if any:   

14. Thesis-related publications:

- Hoang-Quynh Le, Mai-Vu Tran, Thanh Hai Dang, Nigel Collier (2015). The UET-CAM System in the BioCreAtIvE V CDR Task.  In Proceedings of the fifth BioCreative challenge evaluation workshop, Sevilla, Spain, 2015.

- Nigel Collier, Ferdinand Paster, Mai-Vu Tran (2014). The impact of near domain transfer on biomedical named entity recognitions LOUHI 2014, EACL 2014, Sweden, 2014.

- Nigel Collier, Mai-Vu Tran, Hoang-Quynh Le, Quang-Thuy Ha, Anika Oellrich, Dietrich Rebholz-Schuhmann (2013). Learning to Recognize Phenotype Candidates in the Auto-Immune Literature Using SVM Re-Ranking. PLoS ONE 8(10): e72965, October 2013.

- Mai-Vu Tran, Nigel Collier, Hoang-Quynh Le, Van-Thuy Phi and Thanh-Binh Pham (2013). Exploing a Probabilistic Earley Parser for Event Composition in Biomedical Texts, BIONLP-ST:130-134, 2013.

- Mai-Vu Tran, Duc-Trong Le (2013). vTools: Chunker and Part-of-Speech tools, RIVF-VLSP 2013 Workshop.

- Nigel Collier, Mai-Vu Tran, Hoang-Quynh Le, Anika Oellrich, Ai Kawazoe, Martin Hall-May, Dietrich Rebholz-Schuhmann (2012). A Hybrid Approach to Finding Phenotype Candidates in Genetic Texts, COLING 2012: 647-662.

- Mai-Vu Tran, Duc-Trong Le, Xuan-Tu Tran and Tien-Tung Nguyen (2012). A Model of Vietnamese Person Named Entity Question Answering System, PACLIC 2012, Bali, Indonesia, October 2012.

- Mai-Vu Tran, Minh-Hoang Nguyen, Sy-Quan Nguyen, Minh-Tien Nguyen, Xuan-Hieu Phan (2012). VnLoc: A Real–time News Event Extraction Framework for Vietnamese, KSE'2012:161-166, Da Nang, August 17-19, 2012.

- Huyen-Trang Pham, Tien-Thanh Vu, Mai-Vu Tran, Quang-Thuy Ha (2011). A Solution for Grouping Vietnamese Synonym Feature Words in Product Reviews. APSCC 2011: 503-508.

- Hoang-Quynh Le, Mai-Vu Tran, Nhat-Nam Bui, Nguyen-Cuong Phan, Quang-Thuy Ha (2011). An Integrated Approach Using Conditional Random Fields for Named Entity Recognition and Person Property Extraction in Vietnamese Text. IALP 2011:115-118.

- Mai-Vu Tran, Tien-Tung Nguyen, Thanh-Son Nguyen, Hoang-Quynh Le (2010). Automatic Named Entity Set Expansion Using Semantic Rules and Wrappers for Unary Relations. IALP 2010: 170-173.