Weiquan Mao


2022

pdf bib
CSL: A Large-scale Chinese Scientific Literature Dataset
Yudong Li | Yuqing Zhang | Zhe Zhao | Linlin Shen | Weijie Liu | Weiquan Mao | Hui Zhang
Proceedings of the 29th International Conference on Computational Linguistics

Scientific literature serves as a high-quality corpus, supporting a lot of Natural Language Processing (NLP) research. However, existing datasets are centered around the English language, which restricts the development of Chinese scientific NLP. In this work, we present CSL, a large-scale Chinese Scientific Literature dataset, which contains the titles, abstracts, keywords and academic fields of 396k papers. To our knowledge, CSL is the first scientific document dataset in Chinese. The CSL can serve as a Chinese corpus. Also, this semi-structured data is a natural annotation that can constitute many supervised NLP tasks. Based on CSL, we present a benchmark to evaluate the performance of models across scientific domain tasks, i.e., summarization, keyword generation and text classification. We analyze the behavior of existing text-to-text models on the evaluation tasks and reveal the challenges for Chinese scientific NLP tasks, which provides a valuable reference for future research. Data and code will be publicly available.

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
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching
Kunbo Ding | Weijie Liu | Yuejian Fang | Zhe Zhao | Qi Ju | Xuefeng Yang | Rong Tian | Zhu Tao | Haoyan Liu | Han Guo | Xingyu Bai | Weiquan Mao | Yudong Li | Weigang Guo | Taiqiang Wu | Ningyuan Sun
Findings of the Association for Computational Linguistics: NAACL 2022

Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be large in this operation. Otherwise, its performance will drop sharply, thus making it impractical to be deployed to memory-limited devices. To address this issue, we delve into cross-lingual knowledge distillation and propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model. In our framework, contrastive learning, bottleneck, and parameter recurrent strategies are delicately combined to prevent performance from being compromised during the compression process. The experimental results demonstrate that our method can compress the size of XLM-R and MiniLM by more than 50%, while the performance is only reduced by about 1%.

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.