@inproceedings{7ea924bc00134d2385bb6a2c0a098ec4,
title = "Fine-grained coordinated cross-lingual text stream alignment for endless language knowledge acquisition",
abstract = "This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm. We use Burst Information Networks as media to represent text streams and present a simple yet effective network decipherment algorithm with diverse clues to decipher the networks for accurate text stream alignment. Experiments on Chinese-English news streams show our approach not only outperforms previous approaches on bilingual lexicon extraction from coordinated text streams but also can harvest high-quality alignments from large amounts of streaming data for endless language knowledge mining, which makes it promising to be a new paradigm for automatic language knowledge acquisition.",
author = "Tao Ge and Qing Dou and Heng Ji and Lei Cui and Baobao Chang and Zhifang Sui and Furu Wei and Ming Zhou",
note = "Funding Information: We thank the anonymous reviewers for their valuable comments. We also want to thank Xiao-man Pan, Dr. Taylor Cassidy, Dr. Clare R. Voss, Prof. Jiawei Han, Prof. Sujian Li and Prof. Yu Hong for their helpful comments and discussions. This work is supported by NSFC project 61772040 and 61751201. Heng Ji{\textquoteright}s work has been supported by the U.S. DARPA AIDA Program No. FA8750-18-2-0014, Air Force No. FA8650-17-C-7715, ARL NS-CTA No. W911NF-09-2-0053 and NSF Awards IIS-0953149 and IIS-1523198. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on. The contact author is Zhifang Sui. Funding Information: We thank the anonymous reviewers for their valuable comments. We also want to thank Xiaoman Pan, Dr. Taylor Cassidy, Dr. Clare R. Voss, Prof. Jiawei Han, Prof. Sujian Li and Prof. Yu Hong for their helpful comments and discussions. This work is supported by NSFC project 61772040 and 61751201. Heng Ji's work has been supported by the U.S. DARPA AIDA Program No. FA8750-18-2-0014, Air Force No. FA8650-17-C-7715, ARL NS-CTA No. W911NF-09-2-0053 and NSF Awards IIS-0953149 and IIS-1523198. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on. The contact author is Zhifang Sui. Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",
year = "2020",
language = "English (US)",
series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
publisher = "Association for Computational Linguistics",
pages = "2496--2506",
editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
}