148 citations · 509 across the 46 of their papers we have counts for
26 papers · 1 filter
Original or Translated? On the Use of Parallel Data for Translation Quality Estimation
Baopu Qiu, Liang Ding, Di Wu +3
Machine Translation Quality Estimation (QE) is the task of evaluating translation output in the absence of human-written references. Due to the scarcity of human-labeled QE data, p…
Toward Human-Like Evaluation for Natural Language Generation with Error Analysis
Qingyu Lu, Liang Ding, Liping Xie +3
The state-of-the-art language model-based automatic metrics, e.g. BARTScore, benefiting from large-scale contextualized pre-training, have been successfully used in a wide range of…
ContraFeat: Contrasting Deep Features for Semantic Discovery
Xinqi Zhu, Chang Xu, Dacheng Tao
StyleGAN has shown strong potential for disentangled semantic control, thanks to its special design of multi-layer intermediate latent variables. However, existing semantic discove…
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Qihuang Zhong, Liang Ding, Yibing Zhan +11
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language…
Improving Simultaneous Machine Translation with Monolingual Data
Hexuan Deng, Liang Ding, Xuebo Liu +3
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However, the…
From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models
Jiaxian Guo, Junnan Li, Dongxu Li +4
Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. However, effective utilization of LLMs for zero-shot visual question-answer…
Diff-Font: Diffusion Model for Robust One-Shot Font Generation
Haibin He, Xinyuan Chen, Chaoyue Wang +4
Font generation is a difficult and time-consuming task, especially in those languages using ideograms that have complicated structures with a large number of characters, such as Ch…
Responsible Active Learning via Human-in-the-loop Peer Study
Yu-Tong Cao, Jingya Wang, Baosheng Yu +1
Active learning has been proposed to reduce data annotation efforts by only manually labelling representative data samples for training. Meanwhile, recent active learning applicati…
Cross-Modal Contrastive Learning for Robust Reasoning in VQA
Qi Zheng, Chaoyue Wang, Daqing Liu +2
Multi-modal reasoning in visual question answering (VQA) has witnessed rapid progress recently. However, most reasoning models heavily rely on shortcuts learned from training data,…
SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters
Shwai He, Liang Ding, Daize Dong +2
Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tunin…
Knowledge-Aware Federated Active Learning with Non-IID Data
Yu-Tong Cao, Ye Shi, Baosheng Yu +2
Federated learning enables multiple decentralized clients to learn collaboratively without sharing the local training data. However, the expensive annotation cost to acquire data l…
PAD-Net: An Efficient Framework for Dynamic Networks
Shwai He, Liang Ding, Daize Dong +3
Dynamic networks, e.g., Dynamic Convolution (DY-Conv) and the Mixture of Experts (MoE), have been extensively explored as they can considerably improve the model's representation p…
TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
Yu Cao, Dianqi Li, Meng Fang +4
We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models that produces fluent and grammatical adversarial contexts while main…
On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation
Changtong Zan, Liang Ding, Li Shen +3
Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT). However, it usually fails to achieve notable gains (someti…
Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models
Qihuang Zhong, Liang Ding, Li Shen +4
Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware mini…
A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning
Guozheng Ma, Zhen Wang, Zhecheng Yuan +3
Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deployin…
Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition
Mengya Han, Yibing Zhan, Yong Luo +4
Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning pa…
Vega-MT: The JD Explore Academy Translation System for WMT22
Changtong Zan, Keqin Peng, Liang Ding +9
We describe the JD Explore Academy's submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, includin…
PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
Qihuang Zhong, Liang Ding, Juhua Liu +2
Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However,…
Domain-Specific Risk Minimization for Out-of-Distribution Generalization
Yi-Fan Zhang, Jindong Wang, Jian Liang +5
Recent domain generalization (DG) approaches typically use the hypothesis learned on source domains for inference on the unseen target domain. However, such a hypothesis can be arb…
Online Continual Learning with Contrastive Vision Transformer
Zhen Wang, Liu Liu, Yajing Kong +2
Online continual learning (online CL) studies the problem of learning sequential tasks from an online data stream without task boundaries, aiming to adapt to new data while allevia…
Dynamic Contrastive Distillation for Image-Text Retrieval
Jun Rao, Liang Ding, Shuhan Qi +4
Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major d…
Boosting Factorization Machines via Saliency-Guided Mixup
Chenwang Wu, Defu Lian, Yong Ge +3
Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive fea…
Parameter-Efficient and Student-Friendly Knowledge Distillation
Jun Rao, Xv Meng, Liang Ding +2
Knowledge distillation (KD) has been extensively employed to transfer the knowledge from a large teacher model to the smaller students, where the parameters of the teacher are fixe…