BestHub
Sign in
Tagged articles
24 articles
Page 1 of 1
Xiaomi Tech
Xiaomi Tech
Apr 10, 2026 · Artificial Intelligence

Xiaomi AI’s 8× Faster Mobile Inference and OCR‑Free 80‑Page Document Understanding at ACL 2026

Xiaomi’s AI team announced seven ACL 2026 papers that span low‑bit KV‑cache quantization for 8.3× faster LLM inference, OCR‑free multi‑page document VQA, a new attention‑basin analysis, non‑autoregressive spoken dialogue generation, a comprehensive mobile‑agent benchmark, a success‑rate‑aware training policy, and a progressive universal information‑extraction framework.

Inference Optimizationbenchmarkdialogue generation
0 likes · 12 min read
Xiaomi AI’s 8× Faster Mobile Inference and OCR‑Free 80‑Page Document Understanding at ACL 2026
AI Algorithm Path
AI Algorithm Path
Dec 1, 2025 · Artificial Intelligence

Getting Started with the Cutting‑Edge Vision‑Language Model Qwen3‑VL

This article introduces vision‑language models, explains why they outperform OCR‑plus‑LLM pipelines, and walks through practical OCR and information‑extraction tasks using Qwen3‑VL, complete with code snippets, example prompts, result analysis, and a discussion of the model's limitations and resource considerations.

OCRPythonQwen3-VL
0 likes · 13 min read
Getting Started with the Cutting‑Edge Vision‑Language Model Qwen3‑VL
DataFunSummit
DataFunSummit
Nov 1, 2025 · Artificial Intelligence

Large Language Models Revolutionize Legal Document Automation – Alibaba Expert Insights

This article explores how breakthrough large‑model technologies are reshaping legal document automation, covering current challenges, the evolution of intelligent document processing, large‑model applications in core legal scenarios, benchmark results, performance optimizations, and future directions, based on a talk by Alibaba senior algorithm engineer Huang Zhangfeng.

Document AutomationEnterprise ComplianceLegal AI
0 likes · 18 min read
Large Language Models Revolutionize Legal Document Automation – Alibaba Expert Insights
AntTech
AntTech
Aug 13, 2024 · Artificial Intelligence

Ant Group Contributions to ACL 2024: Summaries of 14 Accepted Papers Across NLP and AI

From August 11‑16, 2024 the ACL conference in Bangkok featured 14 Ant Group papers covering large‑scale information extraction, decomposed LLMs for semantic search, multimodal hallucination detection, long‑context attention mechanisms, concept‑reasoning datasets, knowledge‑graph alignment, and more, highlighting the group's breadth in natural language processing and AI research.

ACL2024MultimodalNLP
0 likes · 20 min read
Ant Group Contributions to ACL 2024: Summaries of 14 Accepted Papers Across NLP and AI
DataFunSummit
DataFunSummit
Jun 18, 2024 · Artificial Intelligence

Conditional and Multimodal Knowledge Graph Construction, Extraction, and Integration with Large Models

This article presents a comprehensive overview of conditional and multimodal knowledge graphs, covering their background, construction pipelines, extraction techniques, dataset creation, semi‑supervised learning strategies, and how they can be fused with large language models for enhanced reasoning and application in tasks such as intelligent QA and video scene graph generation.

AIconditional KGinformation extraction
0 likes · 23 min read
Conditional and Multimodal Knowledge Graph Construction, Extraction, and Integration with Large Models
DataFunTalk
DataFunTalk
Jun 14, 2024 · Artificial Intelligence

Shopee's E‑commerce Knowledge Graph Construction and Integration with Large Models

This article presents Shopee's comprehensive exploration of building an e‑commerce knowledge graph, detailing its challenges, construction pipeline, AI‑driven extraction and fusion techniques, multilingual and multimodal modeling, and practical applications ranging from search and recommendation to AI assistants and real‑time updates.

AI applicationsMultimodale-commerce
0 likes · 21 min read
Shopee's E‑commerce Knowledge Graph Construction and Integration with Large Models
DataFunSummit
DataFunSummit
Oct 29, 2023 · Artificial Intelligence

Construction and Application of a Financial Event Knowledge Graph

This article describes the design, construction pipeline, and practical applications of a financial event knowledge graph, covering background challenges, multi‑layer modeling, information‑extraction techniques, and use cases such as institutional risk monitoring, wealth‑management recommendation, and industry‑chain analysis.

Event Extractionfinancial knowledge graphindustry chain analysis
0 likes · 14 min read
Construction and Application of a Financial Event Knowledge Graph
DataFunSummit
DataFunSummit
May 17, 2023 · Artificial Intelligence

Event Extraction: Overview, Methods, and the OmniEvent Toolkit

This article reviews the development of event extraction, explains its importance for knowledge graphs, surveys four major algorithmic paradigms, introduces the OmniEvent open‑source toolkit with its unified benchmark and modular design, and outlines future research directions such as document‑level extraction and event relation modeling.

Event ExtractionNLPinformation extraction
0 likes · 11 min read
Event Extraction: Overview, Methods, and the OmniEvent Toolkit
DataFunSummit
DataFunSummit
Jan 23, 2023 · Artificial Intelligence

Intelligent Document Processing: Core Technologies, Techniques, and Practical Insights

This article explains intelligent document processing (IDP) by describing its core components—OCR, document parsing, and information extraction—detailing various OCR and text‑detection algorithms, discussing document layout reconstruction, table parsing, domain‑specific model adaptation, system optimization, and productization challenges, and outlining future research directions.

AIDocument ParsingIntelligent Document Processing
0 likes · 27 min read
Intelligent Document Processing: Core Technologies, Techniques, and Practical Insights
DataFunTalk
DataFunTalk
Nov 21, 2022 · Artificial Intelligence

Research on Information Extraction from a Graph Perspective

This presentation reviews the background, significance, current research status, objectives, and key contributions of a graph‑based approach to information extraction, covering entity recognition, relation extraction, event extraction, open‑domain extraction, and the proposed unified modeling framework with experimental results.

Graph ModelingNLPentity recognition
0 likes · 27 min read
Research on Information Extraction from a Graph Perspective
DataFunSummit
DataFunSummit
Jul 27, 2022 · Artificial Intelligence

DataFun 2022 Natural Language Processing Summit – Leading Experts Discuss Large‑Scale Language Models, Multimodal Understanding, Dialogue Systems and AI Applications

The DataFun 2022 NLP Summit, held on July 30, brings together top researchers and industry leaders from Alibaba, Baidu, Microsoft, Amazon, and more to present the latest advances in large‑scale pre‑training, multimodal perception, information extraction, dialogue interaction, machine translation, and practical AI deployments, with live streaming and free registration via QR code.

AIDialogue SystemsMultimodal
0 likes · 44 min read
DataFun 2022 Natural Language Processing Summit – Leading Experts Discuss Large‑Scale Language Models, Multimodal Understanding, Dialogue Systems and AI Applications
DataFunTalk
DataFunTalk
Jun 17, 2022 · Artificial Intelligence

OPPO Knowledge Graph: Algorithms, Applications, and Future Directions

This article presents OPPO's large‑scale knowledge graph, detailing the algorithmic challenges and solutions for entity classification, alignment, information extraction, and query parsing, and explains how these techniques power the XiaoBu assistant's knowledge‑based QA, search, and recommendation services while outlining future research directions.

AIOPPOentity alignment
0 likes · 18 min read
OPPO Knowledge Graph: Algorithms, Applications, and Future Directions
Youku Technology
Youku Technology
Feb 28, 2022 · Artificial Intelligence

Seq2Path: Generating Sentiment Tuples as Paths of a Tree

Seq2Path treats each sentiment tuple as an independent tree path, training with average path loss and decoding via constrained beam search with a discriminative token, achieving state‑of‑the‑art results on five aspect‑based sentiment analysis datasets and deployment in Alibaba Entertainment AI Brain.

Beam SearchSentiment AnalysisSeq2Seq
0 likes · 3 min read
Seq2Path: Generating Sentiment Tuples as Paths of a Tree
DataFunTalk
DataFunTalk
Jan 9, 2022 · Artificial Intelligence

Information Extraction for Unstructured Text: From Closed to Open

This presentation reviews the concepts, tasks, and challenges of information extraction from unstructured text, covering closed and open settings, relation extraction, joint extraction, and open extraction methods, and discusses recent advances such as segment‑attention, global‑rationale models, ETL, TPLinker, and maximal‑clique based approaches with experimental results.

information extractionjoint extractionknowledge graph
0 likes · 18 min read
Information Extraction for Unstructured Text: From Closed to Open
DataFunSummit
DataFunSummit
Nov 27, 2021 · Artificial Intelligence

Knowledge Graph Construction, Applications, and Recent Advances in Entity Linking

This article reviews the fundamentals of knowledge graphs, their practical uses in question answering, search and recommendation, and surveys recent research on entity linking—including dual‑encoder retrieval, BERT‑based models, multilingual approaches, and zero‑shot methods—while also outlining modern knowledge‑graph construction pipelines and open challenges.

Machine Learningentity linkinginformation extraction
0 likes · 21 min read
Knowledge Graph Construction, Applications, and Recent Advances in Entity Linking
DataFunTalk
DataFunTalk
Jan 5, 2021 · Artificial Intelligence

OpenIE‑Based Knowledge Graph Construction for Vertical Domains

This article explores the challenges of enterprise knowledge management and presents vertical‑domain knowledge graph construction techniques based on OpenIE, covering data analysis, extraction methods, SPO modeling, both closed‑ and open‑domain approaches, and practical applications such as chatbots, search and intelligent QA.

AIOpenIESPO extraction
0 likes · 12 min read
OpenIE‑Based Knowledge Graph Construction for Vertical Domains
DataFunSummit
DataFunSummit
Dec 9, 2020 · Artificial Intelligence

Construction and Application of Financial Knowledge Graphs: AI Key Technologies, Building Practices, and Real‑World Use Cases

This article explains how financial institutions can leverage massive structured and unstructured data by building a financial knowledge graph, detailing AI core technologies, schema design, extraction methods, storage solutions, and a range of practical applications such as intelligent tagging, recommendation, policy analysis, and executive relationship mining.

Artificial Intelligencefinancial datagraph algorithms
0 likes · 16 min read
Construction and Application of Financial Knowledge Graphs: AI Key Technologies, Building Practices, and Real‑World Use Cases
DataFunTalk
DataFunTalk
Nov 25, 2020 · Artificial Intelligence

Baidu Event Graph: Technology, Construction, and Applications

This article presents Baidu's large‑scale event graph technology, detailing its concepts, construction pipeline, detection, representation, extraction methods, causal relation mining, and real‑world applications such as hotspot discovery, event tracing, resource linking, and causal reasoning, while outlining future research directions.

AIBaiducausal reasoning
0 likes · 22 min read
Baidu Event Graph: Technology, Construction, and Applications
Alibaba Cloud Developer
Alibaba Cloud Developer
Jun 28, 2018 · Artificial Intelligence

How to Build a Knowledge Graph from Scratch: Bottom‑Up Techniques Explained

This article explains the fundamentals of knowledge graphs, compares top‑down and bottom‑up construction methods, describes data types, storage options, logical and technical architectures, and walks through the iterative steps of information extraction, knowledge fusion, processing, updating, and real‑world applications.

Graph Databaseinformation extractionknowledge fusion
0 likes · 18 min read
How to Build a Knowledge Graph from Scratch: Bottom‑Up Techniques Explained