Tagged articles

14 articles

Page 1 of 1

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 ModelingInformation ExtractionNLP

0 likes · 27 min read

Research on Information Extraction from a Graph Perspective

DataFunSummit

Oct 20, 2022 · Artificial Intelligence

End-to-End Speech Relation Extraction

This paper presents an end‑to‑end approach for extracting relational triples directly from speech signals, bypassing intermediate transcription, and demonstrates its effectiveness on synthesized speech versions of the CoNLL04 and TACRED datasets, highlighting challenges such as length constraints and cross‑modal alignment.

End-to-EndMultimodalnatural language processing

0 likes · 17 min read

Laiye Technology Team

Sep 9, 2022 · Artificial Intelligence

Graph Convolutional Networks for Intelligent Document Processing: Principles, Feature Engineering, and Applications

This article presents a comprehensive overview of using graph convolutional networks in intelligent document processing, covering basic GCN theory, adjacency matrix construction, feature engineering—including text, image, and handcrafted features—model architecture, self-supervised training, and real-world applications such as semantic entity recognition and relation extraction.

Intelligent Document Processinggraph convolutional networksrelation extraction

0 likes · 14 min read

Graph Convolutional Networks for Intelligent Document Processing: Principles, Feature Engineering, and Applications

DataFunSummit

Jul 7, 2022 · Artificial Intelligence

Discovering and Enhancing Robustness in Low‑Resource Information Extraction

This article examines the robustness challenges of information extraction tasks such as NER and relation extraction, introduces the Entity Coverage Ratio metric, analyzes why pretrained models like BERT may “take shortcuts,” and proposes evaluation tools and training strategies—including mutual‑information‑based methods, negative‑training, and flooding—to improve model robustness across diverse scenarios.

BERTEvaluation MetricsRobustness

0 likes · 12 min read

Discovering and Enhancing Robustness in Low‑Resource Information Extraction

Code DAO

Apr 10, 2022 · Artificial Intelligence

A Comprehensive Overview of Relation Extraction Techniques

This article surveys relation extraction, defining the task, categorizing its five main forms, and detailing key approaches such as entity position encoding, dependency‑tree methods like shortest dependency path and BRCNN, as well as distant supervision with multi‑instance learning and selective attention.

NLPdependency parsingdistant supervision

0 likes · 12 min read

A Comprehensive Overview of Relation Extraction Techniques

DataFunTalk

Jan 12, 2022 · Artificial Intelligence

Advances in Knowledge Graph Construction: AI Development, Named Entity Recognition, Relation Extraction, and Attribute Completion

This technical report presents a comprehensive overview of artificial intelligence evolution, knowledge‑graph construction techniques—including traditional, cross‑lingual and reading‑comprehension based named entity recognition, weak‑supervised and joint relation extraction, attribute completion via multi‑source cues, and conditional knowledge‑graph modeling—highlighting recent research findings and experimental results.

AI Developmentattribute completionknowledge graph

0 likes · 20 min read

Advances in Knowledge Graph Construction: AI Development, Named Entity Recognition, Relation Extraction, and Attribute Completion

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

DataFunTalk

Dec 1, 2021 · Artificial Intelligence

Awesome Knowledge Graph Resources: Papers, Tools, Datasets, and Projects

This article presents a curated collection of high‑star GitHub "awesome" repositories covering knowledge graph fundamentals, relation extraction, KG‑QA, graph construction, graph neural networks, dynamic graph learning, and multimodal knowledge graphs, providing links, summaries, and key resources for researchers and practitioners.

AI resourcesAwesome Listgraph neural networks

0 likes · 12 min read

Awesome Knowledge Graph Resources: Papers, Tools, Datasets, and Projects

Alibaba Cloud Developer

Apr 19, 2021 · Artificial Intelligence

Explore CBLUE: China’s Premier Biomedical NLP Benchmark and Its 8 Datasets

CBLUE, the Chinese Biomedical Language Understanding Evaluation, offers eight high‑quality medical NLP datasets—including entity extraction, relation extraction, clinical diagnosis normalization, trial criteria classification, semantic similarity, and query relevance—providing a robust benchmark for researchers to test models on real, noisy clinical text.

Biomedical NLPCBLUEClinical Text Classification

0 likes · 8 min read

Explore CBLUE: China’s Premier Biomedical NLP Benchmark and Its 8 Datasets

DataFunTalk

Mar 22, 2020 · Artificial Intelligence

Entity and Relation Extraction: QA-Style Overview of Methods, Challenges, and Recent Advances

This article provides a comprehensive QA‑style review of entity‑relation extraction (ERE), covering pipeline drawbacks, various decoding strategies for NER, common relation‑classification techniques, shared‑parameter and joint‑decoding models, recent transformer‑based approaches, challenges such as overlapping entities, low‑resource settings, and the use of graph neural networks.

Deep LearningNLPentity extraction

0 likes · 32 min read

Entity and Relation Extraction: QA-Style Overview of Methods, Challenges, and Recent Advances

DataFunTalk

Jan 9, 2019 · Artificial Intelligence

Reinforcement Learning in Natural Language Processing: Concepts, Challenges, and Applications

This article introduces reinforcement learning fundamentals, contrasts it with supervised learning, and explores its challenges and advantages in natural language processing, including applications such as text classification, relation extraction from noisy data, and weakly supervised topic segmentation, while summarizing key insights and experimental results.

Reinforcement LearningWeak Supervisionnatural language processing

0 likes · 11 min read

Reinforcement Learning in Natural Language Processing: Concepts, Challenges, and Applications

Alibaba Cloud Developer

Aug 16, 2018 · Artificial Intelligence

How Syntax‑Sensitive Entity Representations Boost Neural Relation Extraction

This paper introduces a syntax‑aware entity representation using Tree‑GRU and attention mechanisms, demonstrating that enriching entity semantics with dependency tree information significantly improves neural relation extraction performance on the NYT dataset compared to existing distant supervision models.

Attention MechanismTree-GRUentity representation

0 likes · 7 min read

How Syntax‑Sensitive Entity Representations Boost Neural Relation Extraction

Alibaba Cloud Developer

Mar 15, 2018 · Artificial Intelligence

How Deep Learning Transforms Knowledge Graph Relation Extraction

This article reviews the evolution from rule‑based DeepDive methods to deep‑learning approaches such as PCNNs and attention‑enhanced models for relation extraction, presents experimental results on the NYT dataset, discusses practical challenges in large‑scale deployment, and outlines future research directions.

Attention MechanismDeep LearningPCNN

0 likes · 14 min read

How Deep Learning Transforms Knowledge Graph Relation Extraction

Alibaba Cloud Developer

Mar 14, 2018 · Artificial Intelligence

DeepDive Powers Knowledge Graph Relation Extraction for Shenma Search

This article explains how Alibaba’s Shenma Search team builds and refines a large‑scale knowledge graph using open information extraction, detailing relation‑extraction techniques, distant supervision challenges, and the DeepDive system’s architecture, custom Chinese NLP pipeline, iterative improvements, and empirical results across millions of triples.

DeepDivedistant supervisionknowledge graph

0 likes · 28 min read