414 citations · 1.4k across the 41 of their papers we have counts for
14 papers · 1 filter
MLP Architectures for Vision-and-Language Modeling: An Empirical Study
Yixin Nie, Linjie Li, Zhe Gan +6
We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks,…
Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
Yichong Xu, Chenguang Zhu, Shuohang Wang +7
Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this…
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Boxin Wang, Chejian Xu, Shuohang Wang +5
Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. Howev…
An Empirical Study of Training End-to-End Vision-and-Language Transformers
Zi-Yi Dou, Yichong Xu, Zhe Gan +9
Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be mo…
Leveraging Knowledge in Multilingual Commonsense Reasoning
Yuwei Fang, Shuohang Wang, Yichong Xu +4
Commonsense reasoning (CSR) requires the model to be equipped with general world knowledge. While CSR is a language-agnostic process, most comprehensive knowledge sources are in fe…
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
Qiyuan Zhang, Lei Wang, Sicheng Yu +4
While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall…
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
Wenhao Yu, Chenguang Zhu, Yuwei Fang +5
Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word sema…
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
Donghan Yu, Chenguang Zhu, Yuwei Fang +6
Current Open-Domain Question Answering (ODQA) model paradigm often contains a retrieving module and a reading module. Given an input question, the reading module predicts the answe…
Want To Reduce Labeling Cost? GPT-3 Can Help
Shuohang Wang, Yang Liu, Yichong Xu +2
Data annotation is a time-consuming and labor-intensive process for many NLP tasks. Although there exist various methods to produce pseudo data labels, they are often task-specific…
LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
Siqi Sun, Yen-Chun Chen, Linjie Li +3
Multimodal pre-training has propelled great advancement in vision-and-language research. These large-scale pre-trained models, although successful, fatefully suffer from slow infer…
Playing Lottery Tickets with Vision and Language
Zhe Gan, Yen-Chun Chen, Linjie Li +6
Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide…
UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training
Mingyang Zhou, Luowei Zhou, Shuohang Wang +4
Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language. To generalize this success to non-English langu…
The Elastic Lottery Ticket Hypothesis
Xiaohan Chen, Yu Cheng, Shuohang Wang +3
Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, which can be trained in isolation to achieve similar or even…
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Xiaohan Chen, Yu Cheng, Shuohang Wang +3
Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous comp…