research
∙
09/16/2023
Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?
Despite the power of Large Language Models (LLMs) like GPT-4, they still...
share
research
∙
05/24/2023
SmartTrim: Adaptive Tokens and Parameters Pruning for Efficient Vision-Language Models
Despite achieving remarkable performance on various vision-language task...
research
∙
05/22/2023
RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text
The fixed-size context of Transformer makes GPT models incapable of gene...
research
∙
05/22/2023
Interactive Natural Language Processing
Interactive Natural Language Processing (iNLP) has emerged as a novel pa...
research
∙
05/18/2023
Efficient Prompting via Dynamic In-Context Learning
The primary way of building AI applications is shifting from training sp...
research
∙
04/27/2023
Controlled Text Generation with Natural Language Instructions
Large language models generate fluent texts and can follow natural langu...
research
∙
01/21/2023
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference
Machine translation quality estimation (QE) predicts human judgements of...
research
∙
11/22/2022
X^2-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
Vision language pre-training aims to learn alignments between vision and...
research
∙
10/21/2022
Efficiently Tuned Parameters are Task Embeddings
Intermediate-task transfer can benefit a wide range of NLP tasks with pr...
research
∙
10/14/2022
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
Pre-trained vision-language models (VLMs) have achieved impressive resul...
research
∙
06/15/2022
Prefix Language Models are Unified Modal Learners
With the success of vision-language pre-training, we have witnessed the ...
research
∙
06/01/2022
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
In this paper, we introduce Cross-View Language Modeling, a simple and e...
research
∙
05/30/2022
VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models
Recent advances in vision-language pre-training (VLP) have demonstrated ...
research
∙
04/08/2022
Contextual Representation Learning beyond Masked Language Modeling
How do masked language models (MLMs) such as BERT learn contextual repre...
research
∙
11/30/2021
Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description
Personalizing dialogue agents is important for dialogue systems to gener...
research
∙
11/08/2021
A Survey on Green Deep Learning
In recent years, larger and deeper models are springing up and continuou...
research
∙
09/07/2021
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression
Recent studies on compression of pretrained language models (e.g., BERT)...
research
∙
06/08/2021
Meta Learning for Knowledge Distillation
We present Meta Learning for Knowledge Distillation (MetaDistil), a simp...
research
∙
05/31/2021
Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training
In this paper, we propose Inverse Adversarial Training (IAT) algorithm f...
research
∙
04/06/2021
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
Cant is important for understanding advertising, comedies and dog-whistl...
research
∙
01/02/2021
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
In this paper, we generalize text infilling (e.g., masked language model...
research
∙
10/11/2020
Connecting the Dots Between Fact Verification and Fake News Detection
Fact verification models have enjoyed a fast advancement in the last two...
research
∙
06/07/2020
BERT Loses Patience: Fast and Robust Inference with Early Exit
In this paper, we propose Patience-based Early Exit, a straightforward y...
research
∙
04/28/2020
Scheduled DropHead: A Regularization Method for Transformer Models
In this paper, we introduce DropHead, a structured dropout method specif...
research
∙
02/12/2020
Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models
Automated evaluation of open domain natural language generation (NLG) mo...
research
∙
02/07/2020
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
In this paper, we propose a novel model compression approach to effectiv...
research
∙
01/31/2020
Pseudo-Bidirectional Decoding for Local Sequence Transduction
Local sequence transduction (LST) tasks are sequence transduction tasks ...
research
∙
01/31/2020
Self-Adversarial Learning with Comparative Discrimination for Text Generation
Conventional Generative Adversarial Networks (GANs) for text generation ...
research
∙
11/07/2019