Recent advances in Named Entity Recognition (NER) show that document-level contexts
can significantly improve model performance. In many application scenarios, however, such …

Pretrained contextualized embeddings are powerful word representations for structured
prediction tasks. Recent work found that better word representations can be obtained by …

Multilingual Language Models (\MLLMs) such as mBERT, XLM, XLM-R,\textit {etc.} have
emerged as a viable option for bringing the power of pretraining to a large number of …

Previous work of class-incremental learning for Named Entity Recognition (NER) relies on
the assumption that there exists abundance of labeled data for the training of new classes. In …

摘要高性能的深度学**网络通常是计算型和参数密集型的, 难以应用于资源受限的边缘设备.
为了能够在低资源设备上运行深度学**模型, 需要研发高效的小规模网络 …

Existing multilingual video corpus moment retrieval (mVCMR) methods are mainly based on
a two-stream structure. The visual stream utilizes the visual content in the video to estimate …

Knowledge distillation (KD) is an effective strategy for neural machine translation (NMT) to
improve the performance of a student model. Usually, the teacher can guide the student to …

The disparity in the languages commonly studied in Natural Language Processing (NLP) is
typically reflected by referring to languages as low vs high-resourced. However, there is …

Fundamental information extraction tasks, such as relation extraction and event detection,
suffer from a data imbalance problem. To alleviate this problem, existing methods rely mostly …

Deep convolutional neural networks (CNNs) have yielded unusually brilliant results in
synthetic aperture radar (SAR) target recognition. However, overparameterization is a widely …