日韩性视频-久久久蜜桃-www中文字幕-在线中文字幕av-亚洲欧美一区二区三区四区-撸久久-香蕉视频一区-久久无码精品丰满人妻-国产高潮av-激情福利社-日韩av网址大全-国产精品久久999-日本五十路在线-性欧美在线-久久99精品波多结衣一区-男女午夜免费视频-黑人极品ⅴideos精品欧美棵-人人妻人人澡人人爽精品欧美一区-日韩一区在线看-欧美a级在线免费观看

歡迎訪問 生活随笔!

生活随笔

當前位置: 首頁 > 编程资源 > 编程问答 >内容正文

编程问答

论文浅尝 |「知识表示学习」专题论文推荐

發布時間:2024/7/5 编程问答 32 豆豆
生活随笔 收集整理的這篇文章主要介紹了 论文浅尝 |「知识表示学习」专题论文推荐 小編覺得挺不錯的,現在分享給大家,幫大家做個參考.

本文轉載自公眾號:PaperWeekly




本期論文清單來自清華大學博士生韓旭和北師大本科生曹書林,涵蓋了近年知識表示學習方向的重要論文




[ 綜述類 ]





■?論文 | Representation Learning: A Review and New Perspectives

■ 鏈接 | https://www.paperweekly.site/papers/1628

■ 源碼 | 無





■?論文 | Knowledge Representation Learning: A Review

■ 鏈接 | https://www.paperweekly.site/papers/1629

■ 源碼 | 無





■?論文 | A Review of Relational Machine Learning for Knowledge Graphs

■ 鏈接 | https://www.paperweekly.site/papers/1630

■ 源碼 | 無





■?論文 | Knowledge Graph Embedding: A Survey of Approaches and Applications

■ 鏈接 | https://www.paperweekly.site/papers/1425

■ 源碼 | 無



[ 期刊 & 頂會 ]





■?論文 | A Three-Way Model for Collective Learning on Multi-Relational Data

■ 鏈接 | https://www.paperweekly.site/papers/1632

■ 源碼 | https://github.com/thunlp/OpenKE





■?論文 | Learning Structured Embeddings of Knowledge Bases

■ 鏈接 | https://www.paperweekly.site/papers/1633

■ 源碼 | 無





■?論文 | A Latent Factor Model for Highly Multi-relational Data

■ 鏈接 | https://www.paperweekly.site/papers/1634

■ 源碼 | 無





■?論文 | Reasoning With Neural Tensor Networks for Knowledge Base Completion

■ 鏈接 | https://www.paperweekly.site/papers/1635

■ 源碼 | 無





■?論文 | Translating Embeddings for Modeling Multi-relational Data

■ 鏈接 | https://www.paperweekly.site/papers/1636

■ 源碼 |?https://github.com/thunlp/OpenKE





■?論文 | Knowledge Graph Embedding by Translating on Hyperplanes

■ 鏈接 | https://www.paperweekly.site/papers/1637

■ 源碼 | https://github.com/thunlp/OpenKE





■?論文 | Learning Entity and Relation Embeddings for Knowledge Graph Completion

■ 鏈接 | https://www.paperweekly.site/papers/1638

■ 源碼 | https://github.com/thunlp/KB2E


擴展閱讀:?


  • Knowledge Representation and Acquisition | 實錄·PhD Talk





■?論文 | Knowledge Graph Embedding via Dynamic Mapping Matrix

■ 鏈接 | https://www.paperweekly.site/papers/1639

■ 源碼 |?https://github.com/thunlp/KB2E





■?論文 | TransA:?An Adaptive Approach for Knowledge Graph Embedding

■ 鏈接 | https://www.paperweekly.site/papers/1640

■ 源碼 | 無


擴展閱讀:?


  • 綜述 | 知識圖譜向量化表示





■?論文 | Learning to Represent Knowledge Graphs with Gaussian Embedding

■ 鏈接 | https://www.paperweekly.site/papers/1641

■ 源碼 | 無




■?論文 | Embedding Entities and Relations for Learning and Inference in Knowledge Bases

■ 鏈接 | https://www.paperweekly.site/papers/1642

■ 源碼 | https://github.com/thunlp/OpenKE





■?論文 | Modeling Relation Paths for Representation Learning of Knowledge Bases

■ 鏈接 | https://www.paperweekly.site/papers/1111

■ 源碼 | https://github.com/thunlp/KB2E


擴展閱讀:?


  • Knowledge Representation and Acquisition | 實錄·PhD Talk




■?論文 | Composing Relationships with Translations

■ 鏈接 | https://www.paperweekly.site/papers/1643

■ 源碼 | 無





■?論文 | From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Prediction

■ 鏈接 | https://www.paperweekly.site/papers/1644

■ 源碼 | 無





■?論文 | TransG : A Generative Model for Knowledge Graph Embedding

■ 鏈接 | https://www.paperweekly.site/papers/1645

■ 源碼 | https://github.com/BookmanHan/Embedding


擴展閱讀:?


  • 一周論文 | 基于翻譯模型(Trans系列)的知識表示學習





■?論文 | Complex Embeddings for Simple Link Prediction

■ 鏈接 | https://www.paperweekly.site/papers/1646

■ 源碼 | https://github.com/ttrouill/complex





■?論文 | Holographic Embeddings of Knowledge Graphs

■ 鏈接 | https://www.paperweekly.site/papers/556

■ 源碼 | https://github.com/mnick/holographic-embeddings





■?論文 | Knowledge Representation Learning with Entities, Attributes and Relations

■ 鏈接 | https://www.paperweekly.site/papers/1647

■ 源碼 |?https://github.com/thunlp/KR-EAR


擴展閱讀:?


  • Knowledge Representation and Acquisition | 實錄·PhD Talk





■?論文 | Knowledge Graph Completion with Adaptive Sparse Transfer Matrix

■ 鏈接 | https://www.paperweekly.site/papers/1648

■ 源碼 |?https://github.com/thunlp/KB2E


擴展閱讀:?


  • 綜述 | 知識圖譜向量化表示





■?論文 | Representation Learning of Knowledge Graphs with Hierarchical Types

■ 鏈接 | https://www.paperweekly.site/papers/1649

■ 源碼 |?https://github.com/thunlp/TKRL


擴展閱讀:?


  • 多源信息表示學習在知識圖譜中的應用 | 實錄·Guru Talk






■?論文 | STransE: A Novel Embedding Model of Entities and Relationships in Knowledge Bases

■ 鏈接 | https://www.paperweekly.site/papers/1650

■ 源碼 | https://github.com/datquocnguyen/STransE





■?論文 | GAKE: Graph Aware Knowledge Embedding

■ 鏈接 | https://www.paperweekly.site/papers/1651

■ 源碼 | https://github.com/JuneFeng/GAKE





■?論文 | Representation Learning of Knowledge Graphs with Entity Descriptions

■ 鏈接 | https://www.paperweekly.site/papers/1652

■ 源碼 |?https://github.com/thunlp/DKRL





■?論文 | Learning First-Order Logic Embeddings via Matrix Factorization

■ 鏈接 | https://www.paperweekly.site/papers/1653

■ 源碼 | 無





■?論文 |?Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

■ 鏈接 | https://www.paperweekly.site/papers/1654

■ 源碼 |?http://www.ibookman.net/conference.html





■?論文 | ProjE: Embedding Projection for Knowledge Graph Completion

■ 鏈接 | https://www.paperweekly.site/papers/1655

■ 源碼 | https://github.com/bxshi/ProjE





■?論文 | Analogical Inference for Multi-Relational Embeddings

■ 鏈接 | https://www.paperweekly.site/papers/1656

■ 源碼 | https://github.com/mana-ysh/knowledge-graph-embeddings





■?論文 | Image-embodied Knowledge Representation Learning

■ 鏈接 | https://www.paperweekly.site/papers/449

■ 源碼 |?https://github.com/xrb92/IKRL


擴展閱讀:?


  • 多源信息表示學習在知識圖譜中的應用 | 實錄·Guru Talk





■?論文 | Iterative Entity Alignment via Joint Knowledge Embeddings

■ 鏈接 | https://www.paperweekly.site/papers/1657

■ 源碼 |?https://github.com/thunlp/IEAJKE





關于PaperWeekly


PaperWeekly 是一個推薦、解讀、討論、報道人工智能前沿論文成果的學術平臺。




OpenKG.CN


中文開放知識圖譜(簡稱OpenKG.CN)旨在促進中文知識圖譜數據的開放與互聯,促進知識圖譜和語義技術的普及和廣泛應用。

點擊閱讀原文,進入 OpenKG 博客。

總結

以上是生活随笔為你收集整理的论文浅尝 |「知识表示学习」专题论文推荐的全部內容,希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯,歡迎將生活随笔推薦給好友。