Tải bản đầy đủ - 0 (trang)
TÀI LIỆU THAM KHẢO

TÀI LIỆU THAM KHẢO

Tải bản đầy đủ - 0trang

[12] T. Barnickel, J. Weston, R. Collobert, H.-W. Mewes, V. St ă umpflen, Large scale

application of neural network based semantic role labeling for automated relation

extraction from biomedical texts, PLoS One 4 (7) (2009) e6393.

[13] Z. Zhao, Z. Yang, L. Luo, H. Lin, J. Wang, Drug drug interaction extraction from

biomedical literature using syntax convolutional neural network, Bioinformatics 32 (22)

(2016) 3444–3453.

[14] H. Zhou, H. Deng, L. Chen, Y. Yang, C. Jia, , D. Huang, Exploiting syntactic and

semantics information for chemical–disease relation extraction, Database (Oxford) 2016

(2016) baw048. doi:10.1093/database/baw048.

[15] F. Mehryary, J. Bj ă orne, S. Pyysalo, T. Salakoski, F. Ginter, Deep learning with

minimal training data: Turkunlp entry in the bionlp shared task 2016, in: Proceedings of

the the 4th BioNLP Shared Task Workshop, Association for Computational Linguistics,

2016, pp. 73–81.

[16] M. Habibi, L. Weber, M. L. Neves, D. L. Wiegandt, U. Leser, Deep learning with

word embeddings improves biomedical named entity recognition, Bioinformatics 33 (14)

(2017) i37–i48.

[17] C. Quan, M. Wang, F. Ren, An unsupervised text mining method for relation

extraction from biomedical literature, PloS one 9 (7) (2014) e102039.

[18] H.-Q. Le, M.-V. Tran, T. H. Dang, Q.-T. Ha, N. Collier, Sieve-based coreference

resolution enhances semi-supervised learning model for chemical-induced disease relation

extraction, Database 2016. doi:https://doi.org/10.1093/database/baw102.

[19] Farrokh Mehryary, Jari Bjăorne, Sampo Pyysalo, Tapio Salakoski, and Filip Ginter.

2016. Deep learning with minimal training data: Turkunlp entry in the bionlp shared task

2016. In Proceedings of the the 4th BioNLP Shared Task Workshop, pages 73–81.

Association for Computational Linguistics

[20] Zhou, H., Deng, H., Chen, L., Yang, Y., Jia, C., Huang, D.: Exploiting syntactic

and semantics information for chemical-disease relation extraction. Database 2016

(04 2016). https://doi.org/10.1093/database/baw048

[21] Can, Duy-Cat, Hoang-Quynh Le, and Quang-Thuy Ha. "Improving Semantic Relation

Extraction System with Compositional Dependency Unit on Enriched Shortest

Dependency Path." In Asian Conference on Intelligent Information and Database Systems,

pp. 140-152. Springer, Cham, 2019.



46



[22] Le, H.Q., Tran, M.V., Dang, T.H., Ha, Q.T., Collier, N.: Sieve-based coreference

resolution enhances semi-supervised learning model for chemical-induced disease relation

extraction. Database 2016 (07 2016). https://doi.org/10.1093/database/baw102.

[23] Zhou, H., Deng, H., Chen, L., Yang, Y., Jia, C., Huang, D.: Exploiting syntactic

and semantics information for chemical{disease relation extraction. Database 2016

(04 2016). https://doi.org/10.1093/database/baw048

[24] Can, Duy-Cat, Hoang-Quynh Le, and Quang-Thuy Ha. "Improving Semantic Relation

Extraction System with Compositional Dependency Unit on Enriched Shortest

Dependency Path." In Asian Conference on Intelligent Information and Database Systems,

pp. 140-152. Springer, Cham, 2019.

[25] Goyal, Kush, and Pushpak Bhattacharyya. "Literature Survey on Relation Extraction

and Relational Learning".

[26] Nanda Kambhatla. 2004. Combining lexical, syntactic, and semantic features with

maximum entropy models for extracting relations. In Proceedings of the ACL 2004 on

Interactive poster and demonstration sessions. Association for Computational Linguistics,

page 22.

[27] Bunescu, R.C., Mooney, R.J.: A shortest path dependency kernel for relation

extraction. In: Proceedings of the conference on human language technology and empirical

methods in natural language processing. pp. 724-731. Association for Computational

Linguistics (2005)



47



PHỤ LỤC 1: TÓM TẮT KẾT QUẢ CID BIOCREATIVE V

Hệ thống



TP



FP



FN



P



R



F1



Dùng từ điển



1341



1799



647



42.71



67.45



52.3



DNorm



1593



370



395



81.15



80.13



80.64



Nhóm 276



1545



549



443



73.78



77.72



75.7



Nhóm 277



1629



191



359



89.51



81.94



85.56



Nhóm 285



1,249



892



739



58.34



62.83



60.5



Nhóm 288



1669



339



319



83.12



83.95



83.53



Nhóm 290



1284



712



704



64.33



64.59



64.46



Nhóm 293



1278



503



710



71.76



64.29



67.82



Nhóm 296



708



66



1280



91.47



35.61



51.27



Nhóm 304



1713



277



275



86.08



86.17



86.12



Nhóm 309



1372



684



616



66.73



69.01



67.85



Nhóm 310



1627



247



361



86.82



81.84



84.26



Nhóm 314



1660



192



328



89.63



83.5



86.46



Nhóm 315



1502



335



486



81.76



75.55



78.54



Nhóm 325



1661



339



327



83.05



83.55



83.3



Nhóm 363



1606



168



382



90.53



80.78



85.38



Nhóm 364



1703



606



285



73.75



85.66



79.26



Nhóm 365



1590



582



398



73.2



79.98



76.44



Trung bình



1487



418



501



78.99



74.81



76.03



(Nguồn: BioCreative V)



48



PHỤ LỤC 2: TÓM TẮT KẾT QUẢ CID BIOCREATIVE V

Hệ thống



TP



FP



FN



P



R



F1



Mức văn bản



815



4145



251



16.43



76.45



27.05



Mức câu



570



1672



496



25.42



53.47



34.46



Nhóm 276



574



544



492



51.34



53.85



52.56



Nhóm 288



623



496



443



55.67



58.44



57.03



Nhóm 289



358



346



708



50.85



33.58



40.45



Nhóm 290



346



536



720



39.23



32.46



35.52



Nhóm 293



354



296



712



54.46



33.21



41.26



Nhóm 299



321



261



745



55.15



30.11



38.96



Nhóm 303



241



199



825



54.77



22.61



32.01



Nhóm 304



552



497



514



52.62



51.78



52.2



Nhóm 310



602



1099



464



35.39



56.47



43.51



Nhóm 316



454



633



612



41.77



42.59



42.17



Nhóm 322



341



462



725



42.47



31.99



36.49



Nhóm 334



441



615



625



41.76



41.37



41.56



Nhóm 335



351



390



715



47.37



32.93



38.85



Nhóm 338



576



635



490



47.56



54.03



50.59



Nhóm 341



408



432



658



48.57



38.27



42.81



Nhóm 363



506



493



560



50.65



47.47



49.01



Nhóm 364



595



1835



471



24.49



55.82



34.04



Nhóm 365



532



464



534



53.41



49.91



51.6



Trung bình



454



569



612



47.09



42.61



43.37



(Nguồn: BioCreative V)



49



Tài liệu bạn tìm kiếm đã sẵn sàng tải về

TÀI LIỆU THAM KHẢO

Tải bản đầy đủ ngay(0 tr)

×