Weijie Liu

Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval

2022 · arXiv (Cornell University)

Zero-shot entity retrieval, aiming to link mentions to candidate entities under the zero-shot setting, is vital for many tasks in Natural Language Processing. Most existing methods represent mentions/entities via the sentence embeddings of corresponding context …

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset

2023 · arXiv (Cornell University)

Federated Learning (FL) is a distributed learning paradigm that can coordinate heterogeneous edge devices to perform model training without sharing private data. While prior works have focused on analyzing FL convergence with respect to hyperparameters …

K-BERT: Enabling Language Representation with Knowledge Graph

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Pre-trained language representation models, such as BERT, capture a general language representation from large-scale corpora, but lack domain-specific knowledge. When reading a domain text, experts make inferences with relevant knowledge. For machines to achieve this …

FastBERT: a Self-distilling BERT with Adaptive Inference Time

2020

Pre-trained language models like BERT have proven to be highly performant. However, they are often computationally expensive in many practical scenarios, for such heavy models can hardly be readily implemented with limited resources. To improve …