Yiren Chen


2022

pdf bib
A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning
Kunbo Ding | Weijie Liu | Yuejian Fang | Weiquan Mao | Zhe Zhao | Tao Zhu | Haoyan Liu | Rong Tian | Yiren Chen
Proceedings of the 29th International Conference on Computational Linguistics

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training multilingual models on English-only resources and transferring them to low-resource languages. However, its effect is limited by the gap between embedding clusters of different languages. To address this issue, we propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embeddings without semantic loss, thereby improving cross-lingual transferability. Experimental results on mBERT and XLM-R demonstrate that our method significantly outperforms previous works on the zero-shot cross-lingual text classification task and can obtain a better multilingual alignment.

pdf bib
Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System
Tao Zhu | Zhe Zhao | Weijie Liu | Jiachi Liu | Yiren Chen | Weiquan Mao | Haoyan Liu | Kunbo Ding | Yudong Li | Xuefeng Yang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track

Catastrophic forgetting is a challenge for model deployment in industrial real-time systems, which requires the model to quickly master a new task without forgetting the old one. Continual learning aims to solve this problem; however, it usually updates all the model parameters, resulting in extensive training times and the inability to deploy quickly. To address this challenge, we propose a parameter-efficient continual learning framework, in which efficient parameters are selected through an offline parameter selection strategy and then trained using an online regularization method. In our framework, only a few parameters need to be updated, which not only alleviates catastrophic forgetting, but also allows the model to be saved with the changed parameters instead of all parameters. Extensive experiments are conducted to examine the effectiveness of our proposal. We believe this paper will provide useful insights and experiences on developing deep learning-based online real-time systems.

2021

pdf bib
Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees
Jiangang Bai | Yujing Wang | Yiren Chen | Yaming Yang | Jing Bai | Jing Yu | Yunhai Tong
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP applications. However, how to incorporate the syntax trees effectively and efficiently into pre-trained Transformers is still unsettled. In this paper, we address this problem by proposing a novel framework named Syntax-BERT. This framework works in a plug-and-play mode and is applicable to an arbitrary pre-trained checkpoint based on Transformer architecture. Experiments on various datasets of natural language understanding verify the effectiveness of syntax trees and achieve consistent improvement over multiple pre-trained models, including BERT, RoBERTa, and T5.