Shuang Wu


pdf bib
ActPerFL: Active Personalized Federated Learning
Huili Chen | Jie Ding | Eric Tramel | Shuang Wu | Anit Kumar Sahu | Salman Avestimehr | Tao Zhang
Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022)

In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training. Such a balance is derived from the inter-client and intra-client uncertainty quantification. Consequently, ActPerFL can adapt to the underlying clients’ heterogeneity with uncertainty-driven local training and model aggregation. With experimental studies on Sent140 and Amazon Alexa audio data, we show that ActPerFL can achieve superior personalization performance compared with the existing counterparts.


MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition
Shuang Wu | Xiaoning Song | Zhenhua Feng
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the information of the Chinese character structure after integrating the lexical information. Chinese characters have evolved from pictographs since ancient times, and their structure often reflects more information about the characters. This paper presents a novel Multi-metadata Embedding based Cross-Transformer (MECT) to improve the performance of Chinese NER by fusing the structural information of Chinese characters. Specifically, we use multi-metadata embedding in a two-stream Transformer to integrate Chinese character features with the radical-level embedding. With the structural characteristics of Chinese characters, MECT can better capture the semantic information of Chinese characters for NER. The experimental results obtained on several well-known benchmarking datasets demonstrate the merits and superiority of the proposed MECT method.