TY - GEN
T1 - Learning named entity tagger using domain-specific dictionary
AU - Shang, Jingbo
AU - Liu, Liyuan
AU - Gu, Xiaotao
AU - Ren, Xiang
AU - Ren, Teng
AU - Han, Jiawei
N1 - We would like to thank Yu Zhang from University of Illinois at Urbana-Champaign for providing results of supervised benchmark methods on the BC5CDR and NCBI datasets. Research was sponsored in part by U.S. Army Research Lab. under Cooperative Agreement No. W911NF-09-2-0053 (NSCTA), DARPA under Agreement No. W911NF-17-C-0099, National Science Foundation IIS 16-18481, IIS 17-04532, and IIS-17-41317, DTRA HDTRA11810026, Google Ph.D. Fellowship and grant 1U54GM114838 awarded by NIGMS through funds provided by the trans-NIH Big Data to Knowledge (BD2K) initiative (www.bd2k.nih.gov). Any opinions, findings, and conclusions or recommendations expressed in this document are those of the author(s) and should not be interpreted as the views of any U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon.
Research was sponsored in part by U.S. Army Research Lab. under Cooperative Agreement No. W911NF-09-2-0053 (NSCTA), DARPA under Agreement No. W911NF-17-C-0099, National Science Foundation IIS 16-18481, IIS 17-04532, and IIS-17-41317, DTRA HD-TRA11810026, Google Ph.D. Fellowship and grant 1U54GM114838 awarded by NIGMS through funds provided by the trans-NIH Big Data to Knowledge (BD2K) initiative (www.bd2k.nih.gov). Any opinions, findings, and conclusions or recommendations expressed in this document are those of the author(s) and should not be interpreted as the views of any U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon.
PY - 2018
Y1 - 2018
N2 - Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features. However, such methods require large amounts of manually-labeled training data. There have been efforts on replacing human annotations with distant supervision (in conjunction with external dictionaries), but the generated noisy labels pose significant challenges on learning effective neural models. Here we propose two neural models to suit noisy distant supervision from the dictionary. First, under the traditional sequence labeling framework, we propose a revised fuzzy CRF layer to handle tokens with multiple possible labels. After identifying the nature of noisy labels in distant supervision, we go beyond the traditional framework and propose a novel, more effective neural model AutoNER with a new Tie or Break scheme. In addition, we discuss how to refine distant supervision for better NER performance. Extensive experiments on three benchmark datasets demonstrate that AutoNER achieves the best performance when only using dictionaries with no additional human effort, and delivers competitive results with state-of-the-art supervised benchmarks.
AB - Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features. However, such methods require large amounts of manually-labeled training data. There have been efforts on replacing human annotations with distant supervision (in conjunction with external dictionaries), but the generated noisy labels pose significant challenges on learning effective neural models. Here we propose two neural models to suit noisy distant supervision from the dictionary. First, under the traditional sequence labeling framework, we propose a revised fuzzy CRF layer to handle tokens with multiple possible labels. After identifying the nature of noisy labels in distant supervision, we go beyond the traditional framework and propose a novel, more effective neural model AutoNER with a new Tie or Break scheme. In addition, we discuss how to refine distant supervision for better NER performance. Extensive experiments on three benchmark datasets demonstrate that AutoNER achieves the best performance when only using dictionaries with no additional human effort, and delivers competitive results with state-of-the-art supervised benchmarks.
UR - http://www.scopus.com/inward/record.url?scp=85071150530&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071150530&partnerID=8YFLogxK
U2 - 10.18653/v1/D18-1230
DO - 10.18653/v1/D18-1230
M3 - Conference contribution
AN - SCOPUS:85071150530
T3 - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
SP - 2054
EP - 2064
BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
A2 - Riloff, Ellen
A2 - Chiang, David
A2 - Hockenmaier, Julia
A2 - Tsujii, Jun'ichi
PB - Association for Computational Linguistics
T2 - 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Y2 - 31 October 2018 through 4 November 2018
ER -