Adapter tuning, which updates only a few parameters, has become a mainst...
Most open-domain dialogue systems suffer from forgetting important
infor...
The multimedia community has shown a significant interest in perceiving ...
Adaptive optimization has achieved notable success for distributed learn...
Egocentric action recognition is gaining significant attention in the fi...
Dense retrievers have achieved impressive performance, but their demand ...
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to h...
Masked language modeling, widely used in discriminative language model (...
Token dropping is a recently-proposed strategy to speed up the pretraini...
Text classification tasks often encounter few shot scenarios with limite...
In federated learning (FL), a cluster of local clients are chaired under...
Random smoothing data augmentation is a unique form of regularization th...
Among generalized additive models, additive Matérn Gaussian Processes (G...
Relation Extraction (RE) is a crucial task in Information Extraction, wh...
The field of deep learning has witnessed significant progress, particula...
Generative large language models (LLMs), e.g., ChatGPT, have demonstrate...
ChatGPT shows remarkable capabilities for machine translation (MT). Seve...
Sharpness aware minimization (SAM) optimizer has been extensively explor...
Federated learning is an emerging distributed machine learning framework...
Recently, ChatGPT has attracted great attention, as it can generate flue...
This technical report briefly describes our JDExplore d-team's submissio...
Partial differential equations (PDEs) have become an essential tool for
...
Machine Translation Quality Estimation (QE) is the task of evaluating
tr...
The state-of-the-art language model-based automatic metrics, e.g. BARTSc...
This technical report briefly describes our JDExplore d-team's Vega v2
s...
Simultaneous machine translation (SiMT) is usually done via sequence-lev...
Dynamic networks have been extensively explored as they can considerably...
Fine-tuning large pretrained language models on a limited training corpu...
Adapter Tuning, which freezes the pretrained language models (PLMs) and ...
We describe the JD Explore Academy's submission of the WMT 2022 shared
g...
Pre-Training (PT) of text representations has been successfully applied ...
Prompt-tuning, which freezes pretrained language models (PLMs) and only
...
Graph Neural Networks (GNNs) tend to suffer from high computation costs ...
Sequence-to-sequence (seq2seq) learning has become a popular trend for
p...
Knowledge distillation (KD) has been extensively employed to transfer th...
We present IBR, an Iterative Backward Reasoning model to solve the proof...
Data augmentations (DA) are the cores to achieving robust
sequence-to-se...
For multilingual sequence-to-sequence pretrained language models
(multil...
Aspect-Based Sentiment Analysis is a fine-grained sentiment analysis tas...
Federated Learning (FL) is an emerging distributed learning paradigm und...
This paper seeks to provide the information retrieval community with som...
We develop an exact and scalable algorithm for one-dimensional Gaussian
...
We present a simple and effective pretraining strategy Denoising
Trainin...
Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentime...
Deep Gaussian Processes (DGP) enable a non-parametric approach to quanti...
Aspect-based Sentiment Analysis (ABSA) aims to determine the sentiment
p...
Pre-training (PT) and back-translation (BT) are two simple and powerful
...
We present a simple and effective pretraining strategy – bidirectional
t...
This paper describes the University of Sydney JD's joint submission o...
High-dimensional simulation optimization is notoriously challenging. We
...