Home
Publications
Research Areas
Data Science and Data Mining
Natural Language and Speech
Business Intelligence
Robotics and Autonomous Driving
Computer Vision
Machine Learning and Deep Learning
Computational Biology and Bioinformatics
High Performance Computing
Quantum Computing
Blog
Careers
Downloads
AI Colloquium
Home
Publications
Research Areas
Data Science and Data Mining
Natural Language and Speech
Business Intelligence
Robotics and Autonomous Driving
Computer Vision
Machine Learning and Deep Learning
Computational Biology and Bioinformatics
High Performance Computing
Quantum Computing
Blog
Careers
Downloads
AI Colloquium
Natural Language and Speech
PUBLICATIONS
A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass Deliberation
EMNLP 2023
Natural Language and Speech
Actively Supervised Clustering for Open Relation Extraction
ACL 2023
Natural Language and Speech
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
ACL 2023
Natural Language and Speech
Connectivity Patterns are Task Embeddings
ACL 2023
Natural Language and Speech
MORE
BLOG
Baidu Presents Top 10 Frontier Technology Inventions of 2022
Baidu yesterday announced its first list of Top 10 Frontier Technology Invention...
Introducing PCL-BAIDU Wenxin (ERNIE 3.0 Titan), the World’s First Knowledge Enhanced Multi-Hundred-Billion Model
We are excited to introduce PCL-BAIDU Wenxin (or “ERNIE 3.0 Titan”), a pre-tra...
Baidu Releases PLATO-XL: World’s First 11 Billion Parameter Pre-Trained Dialogue Generation Model
Now Baidu PLATO-2 has been upgraded to PLATO-XL. Over ten billion parameters mak...
Baidu at ACL-IJCNLP 2021
The first-ever Joint Conference of the 59th Annual Meeting of the Association fo...
ERNIE 3.0 Achieves State-of-the-Art Results in 54 Chinese NLP Tasks, Crowned 1st Place on SuperGLUE Leaderboard
Baidu Research has proposed a unified framework, coined as ERNIE 3.0, for pre-tr...
PaddlePaddle’s Graph Neural Networks Advance Drug Design
Our AI models, trained with Baidu’s open-source deep learning platform PaddlePa...
Call For Papers! The Inaugural ICDAR Workshop on Document Image and Language (DIL 2021)
Baidu, together with CASIA, DFKI, and the State University of New York at Buffal...
Baidu at AAAI 2021: Multimodal Transformer, Supervised Quantum Learning, Early Detection of COVID-19 High-Risk Areas
The 35th annual AAAI Conference on Artificial Intelligence is now underway from...
ERNIE-M: Multilingual Model Learns 96 Languages from Monolingual Corpora, Tops Google’s XTREME Benchmark
ERNIE-M delivers new SOTA results across five cross-lingual NLP tasks and tops t...
Baidu Research: 10 Technology Trends in 2021
Baidu Research is releasing our prediction of the 10 major scientific and techno...
2020 Retrospective: Baidu’s AI Innovations
Before we start our 2021 journey, we want to take a quick look at the AI innovat...
Inside RocketQA: AI Powers Search Engine to Provide the Best Possible Answer
We are excited to introduce RocketQA, a novel training approach to dense passage...
Exploring Baidu Brain 6.0: Updated PaddlePaddle, 2nd-Gen AI Processor, and New Quantum Computing Platform
Join us for a quick look at Baidu Brain 6.0, including new updates in Baidu’s d...
Introducing Qian Yan, Baidu's New Plan to Build 100 Chinese NLP Datasets in Three Years
As Baidu NLP turns 10 this year, we are thrilled to announce new plans and produ...
PLATO-2: The State-of-the-art Open-Domain Chatbot in Chinese and English
We are excited to present PLATO-2, our newest open-domain chatbot model that can...
Baidu’s Multimodal Model ERNIE-ViL Achieves SOTA on 5 Tasks and Tops Visual Commonsense Reasoning Challenge
We are proud to introduce ERNIE-ViL, a knowledge-enhanced approach to learn join...
WaveFlow: A Compact Flow-Based Model for Raw Audio
Baidu announced WaveFlow (paper, audio samples), the latest milestone of audio s...
Baidu Research: 10 Technological Trends in 2020
In the past year alone, the integration of multiple emerging technologies has sp...
Baidu’s Pre-training Model ERNIE Achieves New NLP Benchmark Record
Today we are excited to announce that ERNIE has achieved new state-of-the-art pe...
Baidu PaddlePaddle Releases 21 New Capabilities to Accelerate Industry-Grade Model Development
Featuring 100+ models, new mobile inference engine, and frameworks for graph & f...
Baidu Research launched the
The "Polaris Program" of Baidu Research provides the most advanced and cutting-e...
Baidu releases DuTongChuan: A Context-aware Translation Model for Simultaneous Interpreting
Here we announce DuTongChuan, the first context-aware translation model for sim...
Baidu’s Optimized ERNIE Achieves State-of-the-Art Results in Natural Language Processing Tasks
Baidu today released ERNIE 2.0 (Enhanced Representation through kNowledge IntEgr...
Baidu Research Bolsters Capabilities with New Labs and World-renowned Appointment to Advisory Board
Baidu Research now counts seven major research labs and welcomes Artur Konrad Ek...
Hubless Nearest Neighbor Search for Bilingual Lexicon Induction
This blogpost introduces our recent publication in ACL 2019....
10 Papers from Baidu Accepted by Association for Computational Linguistics 2019 Annual Meeting
Baidu’s research in Natural Language Processing is highly recognized....
Parallel Neural Text-to-Speech
Text-to-Speech (TTS), also called speech synthesis, has a variety of application...
Baidu released knowledge integration language representation model ERNIE which outperforms Google’s BERT in certain Chinese NLP tasks
Baidu released ERNIE (Enhanced Representation from kNowledge IntEgration) with i...
Baidu Team Wins the Suggestion Mining Challenge at SemEval 2019
Baidu triumphed over 210 teams from around the world in the 13th International W...
Baidu Teams up with Academia, awarding Grand Prizes for Breakthroughs in the ICDAR 2019 Competitions
The Competitions of International Conference on Document Analysis and Recognitio...
A Breakthrough in Speech Technology: Baidu Launched SMLTA, the First Streaming Multi-layer Truncated Attention Model for Large-scale Online Speech Recognition
On 16 January 2019, Baidu announced four major breakthroughs in automatic speech...
Baidu Research Establishes an Advisory Board, Holds 1st Board Meeting in Silicon Valley
Baidu Research brings together more world-renowned scientists to jointly advance...
Baidu Research Announces Breakthrough in Simultaneous Translation
STACL, or Simultaneous Translation with Anticipation and Controllable Latency, i...
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
ClariNet, the first end-to-end TTS model, directly converts text to a speech wav...
The Association for Computational Linguistics Appoints Baidu’s Haifeng Wang as the Founding Chair of the Newly Launched Asia-Pacific Chapter
Today, at the 56th Annual Meeting of the Association for Computational Linguisti...
Language Acquisition and One-Shot Concept Learning Through Conversational Interactions
Building intelligent agents that can communicate naturally with and learn effect...
Neural Voice Cloning with a Few Samples
At Baidu Research, we aim to revolutionize human-machine interfaces with the lat...
Baidu Research Showcased at Top Artificial Intelligence Conferences
The AAAI (Association for the Advancement of Artificial Intelligence) is one of...
Deep Speech 3: Even more end-to-end speech recognition
Accurate speech recognition systems are vital to many businesses, whether they a...
Deep Voice 3: 2000-Speaker Neural Text-to-Speech
Today, we are excited to announce Deep Voice 3, the latest milestone of Baidu Re...
Globally Normalized Reader
We present the Globally Normalized Reader - an approach to extractive question a...
Learning to Speak via Interaction
In early April, our team at Baidu Research successfully taught an AI agent to na...
Deep Voice 2: Multi-Speaker Neural Text-to-Speech
In February, Baidu Silicon Valley AI Lab published Deep Voice 1, a system for ge...
Deep Speaker: an End-to-End System for Large-Scale Speaker Recognition
Speaker recognition algorithms seek to determine the identity of a speaker from...
An AI agent with human-like language acquisition in a virtual environment
Despite tremendous progress, artificial intelligence is still limited in many wa...