Publications

FML-19： Multi-task Learning for Vertical Federated Machine Learning: A Case Study For Cross-Lingual Short-Text Matching

Published in The 1st International Workshop on Federated Machine Learning for User Privacy and Data Confidentiality (FML-19) in conjunction with the 28th International Joint Conference on Artificial Intelligence (IJCAI-19), 2019

Brief Introduction : This paper is about vertical federated machine learning on cross-lingual short-text matching and accepted by FML-19(a workshop in IJCAI-19). In this paper, we propose a vertical federated learning framework using multi-task learning.

Authors : Bo Li, Kele Xu, Haibo Mi, Dawei Feng, Huaimin Wang and Yanbo J. Wang

Place : Macau‚ China

Date : Aug 12th, 2019

ACL2019： Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data

Published in The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019), 2019

Brief Introduction : This paper is about Relation Extraction and Relation Identification and accepted by ACL2019. In this paper, we use tag embeddings and improved multi-task learning to obtain the state-of-the-art performances on ACE2005 Chinese and English corpus.

Authors : Wei Ye^, Bo Li^, Rui Xie, Zhonghao Sheng, Long Chen and Shikun Zhang. (^indicates co-first author)

Place : Florence, Italy

Date : July 28th to August 2nd, 2019

ICASSP2019： Long Text Analysis Using Sliced Recurrent Neural Networks With Breaking Point Information Enrichment

Published in Proceedings of the 2019 IEEE International Conference on Acoustics‚ Speech and Signal Processing (ICASSP2019), 2019

Brief Introduction : This paper is about long text classification problem and accepted by ICASSP2019. In this paper, based on SRNN, we propose a breaking point information enrichment mechanism to strengthen dependencies between sliced subsequences without hindering parallelization.

Authors : Bo Li^‚ Zehua Cheng^‚ Zhenghua Xu‚ Wei Ye‚ Thomas Lukasiewicz and Shikun Zhang. (^indicates co-first author)

Place : Brighton‚ UK

Date : May 12th−17th, 2019

ICASSP2019： Denoising Convolutional Autoencoder Based B-Mode Ultrasound Tongue Image Feature Extraction

Published in Proceedings of the 2019 IEEE International Conference on Acoustics‚ Speech and Signal Processing (ICASSP2019), 2019

Brief Introduction : This paper is about feature extraction in the ultrasound tongue image and accepted by ICASSP2019. In this paper, we explore unsupervised convolutional network architecture for the feature extraction in the ultrasound tongue image which can be helpful for the clinical linguist and phonetics.

Authors : Bo Li, Kele Xu, Dawei Feng, Haibo Mi, Huaimin Wang, Jian Zhu

Place : Brighton‚ UK

Date : May 12th−17th, 2019

ICIC2018： Multi-Scale DenseNet-Based Electricity Theft Detection

Published in 2018 Fourteenth International Conference on Intelligent Computing (ICIC2018), 2018

Brief Introduction : This paper is about electricity theft detection based on Multi-scale DenseNet and accepted by ICIC2018. In this paper, we present a novel approach for automatic detection by using a multi-scale dense connected convolution neural network (multi-scale DenseNet) in order to capture the long-term and short-term periodic features within the sequential data.

Authors : Bo Li, Kele Xu, Xiaoyan Cui, Yiheng Wang, Xinbo Ai, Yanbo Wang

Place : Wuhan‚ China

Date : August 15th-18th, 2018