research
∙
09/08/2023
GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue
Pre-trained models have achieved success in Chinese Short Text Matching ...
share
research
∙
08/28/2023
An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
Consistency regularization methods, such as R-Drop (Liang et al., 2021) ...
research
∙
06/12/2023
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
Multilingual sentence representations are the foundation for similarity-...
research
∙
06/02/2023
A Simple yet Effective Self-Debiasing Framework for Transformer Models
Current Transformer-based natural language understanding (NLU) models he...
research
∙
05/18/2023
Learning In-context Learning for Named Entity Recognition
Named entity recognition in real-world applications suffers from the div...
research
∙
05/12/2023
Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
The multilingual neural machine translation (NMT) model has a promising ...
research
∙
02/28/2023
SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases
Recent studies reveal that various biases exist in different NLP tasks, ...
research
∙
02/09/2023
ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models
In recent years, there has been an increased popularity in image and spe...
research
∙
01/09/2023
ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization
Task-agnostic knowledge distillation attempts to address the problem of ...
research
∙
01/09/2023
Universal Information Extraction as Unified Semantic Matching
The challenge of information extraction (IE) lies in the diversity of la...
research
∙
12/19/2022
Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
The quality of knowledge retrieval is crucial in knowledge-intensive con...
research
∙
12/13/2022
ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
Software engineers working with the same programming language (PL) may s...
research
∙
11/09/2022
ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation
Recent cross-lingual cross-modal works attempt to extend Vision-Language...
research
∙
11/07/2022
ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech
Speech representation learning has improved both speech understanding an...
research
∙
11/02/2022
PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
Recently, the practical deployment of open-domain dialogue systems has b...
research
∙
10/27/2022
ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts
Recent progress in diffusion models has revolutionized the popular techn...
research
∙
10/24/2022
A Practical Distributed ADMM Solver for Billion-Scale Generalized Assignment Problems
Assigning items to owners is a common problem found in various real-worl...
research
∙
10/21/2022
Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards
Derivative-free prompt learning has emerged as a lightweight alternative...
research
∙
10/16/2022
CDConv: A Benchmark for Contradiction Detection in Chinese Conversations
Dialogue contradiction is a critical issue in open-domain dialogue syste...
research
∙
10/14/2022
Q-TOD: A Query-driven Task-oriented Dialogue System
Existing pipelined task-oriented dialogue systems usually have difficult...
research
∙
10/12/2022
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Recent years have witnessed the rise and success of pre-training techniq...
research
∙
09/30/2022
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training
Recent Vision-Language Pre-trained (VLP) models based on dual encoder ha...
research
∙
08/30/2022
Towards Boosting the Open-Domain Chatbot with Human Feedback
Many open-domain dialogue models pre-trained with social media comments ...
research
∙
08/26/2022
SeSQL: Yet Another Large-scale Session-level Chinese Text-to-SQL Dataset
As the first session-level Chinese dataset, CHASE contains two separate ...
research
∙
08/11/2022
GEM-2: Next Generation Molecular Property Prediction Network with Many-body and Full-range Interaction Modeling
Molecular property prediction is a fundamental task in the drug and mate...
research
∙
07/28/2022
An Interpretability Evaluation Benchmark for Pre-trained Language Models
While pre-trained language models (LMs) have brought great improvements ...
research
∙
07/28/2022
HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative
AI-based protein structure prediction pipelines, such as AlphaFold2, hav...
research
∙
06/28/2022
SINC: Service Information Augmented Open-Domain Conversation
Generative open-domain dialogue systems can benefit from external knowle...
research
∙
06/06/2022
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
We introduce Bi-SimCut: a simple but effective training strategy to boos...
research
∙
05/25/2022
Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation
Many recent works indicate that the deep neural networks tend to take da...
research
∙
05/23/2022
A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
While there is increasing concern about the interpretability of neural m...
research
∙
05/18/2022
ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval
Neural retrievers based on pre-trained language models (PLMs), such as d...
research
∙
05/17/2022
HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer
Accurate ADMET (an abbreviation for "absorption, distribution, metabolis...
research
∙
04/22/2022
Towards Multi-Turn Empathetic Dialogs with Positive Emotion Elicitation
Emotional support is a crucial skill for many real-world scenarios, incl...
research
∙
04/15/2022
Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals
Most dialog systems posit that users have figured out clear and specific...
research
∙
03/23/2022
Unified Structure Generation for Universal Information Extraction
Information extraction suffers from its varying targets, heterogeneous s...
research
∙
03/19/2022
DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
In this paper, we present DuReader_retrieval, a large-scale Chinese data...
research
∙
03/17/2022
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
Despite recent progress of pre-trained language models on generating flu...
research
∙
03/17/2022
UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Vision-Language Pre-training (VLP) has achieved impressive performance o...
research
∙
03/17/2022
DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Due to the limitations of the model structure and pre-training objective...
research
∙
03/11/2022
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Most of the open-domain dialogue models tend to perform poorly in the se...
research
∙
12/31/2021
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation
Conventional methods for the image-text generation tasks mainly tackle t...
research
∙
12/23/2021
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Pre-trained language models have achieved state-of-the-art results in va...
research
∙
12/23/2021
TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations
Task-oriented dialogue systems have been plagued by the difficulties of ...
research
∙
12/16/2021
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
In this paper, we focus on studying robustness evaluation of Chinese que...
research
∙
11/18/2021
Docking-based Virtual Screening with Multi-Task Learning
Machine learning shows great potential in virtual screening for drug dis...
research
∙
10/29/2021
Amendable Generation for Dialogue State Tracking
In task-oriented dialogue systems, recent dialogue state tracking method...
research
∙
10/25/2021
SgSum: Transforming Multi-document Summarization into Sub-graph Selection
Most of existing extractive multi-document summarization (MDS) methods s...
research
∙
10/14/2021
Building Chinese Biomedical Language Models via Multi-Level Text Discrimination
Pre-trained language models (PLMs), such as BERT and GPT, have revolutio...
research
∙
09/20/2021