84 citations · 274 across the 15 of their papers we have counts for
15 papers
Recouple Event Field via Probabilistic Bias for Event Extraction
Xingyu Bai, Taiqiang Wu, Han Guo +7
Event Extraction (EE), aiming to identify and classify event triggers and arguments from event mentions, has benefited from pre-trained language models (PLMs). However, existing PL…
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching
Kunbo Ding, Weijie Liu, Yuejian Fang +3
Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks.…
Fully Self-Supervised Learning for Semantic Segmentation
Yuan Wang, Wei Zhuo, Yucong Li +3
In this work, we present a fully self-supervised framework for semantic segmentation(FS^4). A fully bootstrapped strategy for semantic segmentation, which saves efforts for the hug…
Semantic Matching from Different Perspectives
Weijie Liu, Tao Zhu, Weiquan Mao +4
In this paper, we pay attention to the issue which is usually overlooked, i.e., \textit{similarity should be determined from different perspectives}. To explore this issue, we rele…
Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation
Ke Zhang, Sihong Chen, Qi Ju +3
With the increase in the number of image data and the lack of corresponding labels, weakly supervised learning has drawn a lot of attention recently in computer vision tasks, espec…
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
Chen Xu, Bojie Hu, Yanyang Li +5
Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Autom…
Energy Aligning for Biased Models
Bowen Zhao, Chen Chen, Qi Ju +1
Training on class-imbalanced data usually results in biased models that tend to predict samples into the majority classes, which is a common and notorious problem. From the perspec…
Dynamic Curriculum Learning for Low-Resource Neural Machine Translation
Chen Xu, Bojie Hu, Yufan Jiang +6
Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this…
Code-switching pre-training for neural machine translation
Zhen Yang, Bojie Hu, Ambyera Han +2
This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which…
FastBERT: a Self-distilling BERT with Adaptive Inference Time
Weijie Liu, Peng Zhou, Zhe Zhao +3
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…
A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection
Pei Xu, Shan Huang, Hongzhen Wang +3
Chinese keyword spotting is a challenging task as there is no visual blank for Chinese words. Different from English words which are split naturally by visual blanks, Chinese words…
RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices
Chen Chen, Mengyuan Liu, Xiandong Meng +2
Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Ther…
K-BERT: Enabling Language Representation with Knowledge Graph
Weijie Liu, Peng Zhou, Zhe Zhao +4
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 dom…
UER: An Open-Source Toolkit for Pre-training Models
Zhe Zhao, Hui Chen, Jinbin Zhang +7
Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks. While there does not exist a single pre-training model that works best in all c…
Improving Image Captioning with Conditional Generative Adversarial Nets
Chen Chen, Shuai Mu, Wanpeng Xiao +3
In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-…