Tagged articles
information extraction
24 articles · Page 1 of 1
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.
Document UnderstandingInference OptimizationLarge Language Models
0 likes · 12 min read

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.
Deep LearningOCRPython
0 likes · 13 min read

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.
Enterprise ComplianceLarge Language ModelsLegal AI
0 likes · 18 min read


AntTechAug 13, 2024 · Artificial Intelligence
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.
ACL2024Large Language ModelsNLP
0 likes · 20 min read

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.
AILarge Language Modelsconditional KG
0 likes · 23 min read

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 applicationsLarge Language Modelse-commerce
0 likes · 21 min read

This article reviews the rapid progress of large language models, compares them with knowledge graphs, explores how LLMs can aid knowledge extraction and completion, discusses how knowledge graphs can evaluate and enhance LLMs, and outlines future interactive integration between the two technologies.
AIEvaluationLarge Language Models
0 likes · 12 min read

This article demonstrates how to leverage ChatGPT to automatically extract structured key information from conversational text by defining input keywords, crafting effective prompts, testing iterative refinements, and integrating the process into a Coze workflow that outputs clean JSON data.
AIJSONinformation extraction
0 likes · 8 min read

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 ExtractionRecommendation Systemfinancial knowledge graph
0 likes · 14 min read

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

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.
AIIntelligent Document ProcessingOCR
0 likes · 27 min read

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

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 SystemsLarge Language Models
0 likes · 44 min read

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

This article explains how PaddleNLP's Universal Information Extraction (UIE) model can dramatically reduce labeling effort and improve accuracy for logistics parcel data extraction, showcasing a five‑sample experiment that boosts F1 by 18 points to 93% and providing a zero‑shot Python example.
NLPPaddleNLPPython
0 likes · 5 min read

This article introduces PaddleNLP's UIE tool for open‑domain information extraction, explains its underlying UIE model and ERNIE 3.0 foundation, showcases concise Python code for entity and event extraction, and presents few‑shot and SOTA performance results across multiple IE benchmarks.
Few-Shot LearningPaddleNLPPython
0 likes · 11 min read

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.
ACLSeq2SeqTree Structure
0 likes · 3 min read

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

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.
entity linkinginformation extractionknowledge graph
0 likes · 21 min read

This article analyzes Xianyu's second‑hand attribute extraction pipeline, detailing the challenges of sparse product data, the decomposition into NER and classification tasks, the use of Albert‑Tiny, StructBert and regex methods, deployment strategies, evaluation results, and future directions.
ALBERTNLPStructBert
0 likes · 11 min read

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

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.
Graph AlgorithmsSemantic Searchartificial intelligence
0 likes · 16 min read

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

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.
Knowledge Fusiongraph databaseinformation extraction
0 likes · 18 min read
