必读论文｜实体链接经典论文推荐47篇

最新推荐文章于 2024-03-24 15:46:26 发布
最新推荐文章于 2024-03-24 15:46:26 发布
阅读量1.6k 收藏 23
点赞数 5
分类专栏： 论文笔记 文章标签： 知识图谱 自然语言处理 人工智能
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_43586043/article/details/119772436
版权

实体链接（entity linking）的任务是识别出文本中的提及（mention） 并建立起到知识库实体（entity）的链接，将非结构化数据连接到结构化数据。实体链接利用知识库中大量实体的丰富信息，实现各种语义应用，如实体链接是很多信息抽取（IR）和自然语言理解（NLU）pipeline 中的重要组件，因为它能够消除文本中 mention 的歧义，并确定 mention 的正确含义。

本文按照 2020 年综述 “Neural Entity Linking: A Survey of Models Based on Deep Learning” 中对主流方法的分类，结合多个 Benchmark 的 SOTA 模型，整理出 2021 年及以前的 47 篇值得一读的实体链接领域的论文

General Architecture

Candidate Generation

surface form matching
  1. "Combining word and entity embeddings for entity linking" Jose G. Moreno, Romaric Besancon , Romain Beaumont (ESWC 2017) [paper] [code]
dictionary lookup

  1. "Personalized page rank for named entity disambiguation" Maria Pershina, Yifan He, Ralph Grishman (NAACL 2015)[paper] [code]

  2. "YAGO A core of semantic knowledge unifying wordnet and wikipedia" Fabian M. Suchanek, Gjergji Kasneci, Gerhard Weikum (www 2007) [paper] [code]

prior probability

  1. "A Cross-Lingual Dictionary for English Wikipedia Concepts" Valentin I. Spitkovsky, Angel X. Chang (LREC 2012) [paper] [code]

  2. "Deep joint entity disambiguation with local neural attention" Octavian-Eugen Ganea, Thomas Hofmann (EMNLP 2017) [paper] [code]

Context-Mention Encoding

recurrent architecture

  1. "Entity linking via joint encoding of types, descriptions, and context" Nitish Gupta, Sameer Singh, Dan Roth (EMNLP 2017) [paper] [code]

  2. "End-to-end neural entity linking" Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann (CoNLL 2018) [paper] [code]

  3. "Neural cross-lingual entity linking" Avirup Sil, Gourab Kundu, Radu Florian, Wael Hamza (AAAI 2018) [paper] [code]

self-attention

  1. "Zero-shot entity linking by reading entity descriptions" Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee (ACL 2019) [paper] [code]

  2. "Scalable Zero-shot Entity Linking with Dense Entity Retrieval" Ledell Wu, Fabio Petroni, Martin Josifoski (EMNLP 2020) [paper] [code]

  3. "Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities" Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto (2019) [paper] [code]

Entity Encoding

pre-trained：基于原始标注文本

  1. "Combining word and entity embeddings for entity linking" Jose G. Moreno, Romaric Besancon , Romain Beaumont (ESWC 2017) [paper] [code]

  2. "Robust and Collective Entity Disambiguation through Semantic Embeddings Stefan" Stefan Zwicklbauer, Christin Seifert, Michael Granitzer (SIGIR 2016) [paper] [code]

  3. "Jointly Embedding Entities and Text with Distant Supervision" Denis Newman-Griffis, Albert M Lai, Eric Fosler-Lussier (ACL 2018) [paper] [code]

  4. "Improving neural entity disambiguation with graph embeddings" Özge Sevgili, Alexander Panchenko, Chris Biemann (ACL 2019) [paper] [code]

joint encoding and ranking

  1. "Learning dense representations for entity retrieval" Daniel Gillick, Sayali Kulkarni, Larry Lansing, (CoNLL 2019) [[paper]](./papers/Gillick et al. - 2019 - Learning dense representations for entity retrieval.pdf) [code]

  2. "Entity linking via joint encoding of types, descriptions, and context" Nitish Gupta, Sameer Singh, Dan Roth (EMNLP 2017) [paper] [code]

  3. "Zero-shot entity linking by reading entity descriptions" Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee (ACL 2019) [paper] [code]

Unlinkable Mention Prediction

no candidate

  1. "Neural cross-lingual entity linking" Avirup Sil, Gourab Kundu, Radu Florian, Wael Hamza (AAAI 2018) [paper] [code]

  2. "Cross-lingual Wikification Using Multilingual Embeddings" Chen-Tse Tsai, Dan Roth (NAACL 2016) [paper] [code]

threshold

  1. "Plato A Selective Context Model for Entity Resolution" Nevena Lazic, Amarnag Subramanya, Michael Ringgaard, Fernando Pereira (TACL 2015)[paper] [code]

  2. "Knowledge enhanced word representation" Matthew E. Peters, Mark Neumann, Robert Logan (EMNLP 2019) [paper] [code]

NIL predictor
  1. "End-to-end neural entity linking" Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann (CoNLL 2018) [paper] [code]
separate model

  1. "Joint learning of named entity recognition and entity linking" Pedro Henrique Martins, Zita Marinho, André F. T. Martins (ACL 2019) [paper] [code]

  2. "Combining word and entity embeddings for entity linking" Jose G. Moreno, Romaric Besancon , Romain Beaumont (ESWC 2017) [paper] [code]

Modifications of the General Architecture

Joint Entity Recognition and Disambiguation Architecture

candidate based

  1. "End-to-end neural entity linking" Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann (CoNLL 2018) [paper] [code]

  2. "Knowledge enhanced word representation" Matthew E. Peters, Mark Neumann, Robert Logan (EMNLP 2019) [paper] [code]

multitask learning
  1. "Joint learning of named entity recognition and entity linking" Pedro Henrique Martins, Zita Marinho, André F. T. Martins (ACL 2019) [paper] [code]
sequence labeling
  1. "Investigating entity knowledge in BERT with simple neural end-to-end entity linking" Samuel Broscheit (CoNLL 2019) [paper] [code]

Global Context Architecture

random walk based

  1. "Robust named entity disambiguation with random walks" Zhaochen Guo, Denilson Barbosa (SWJ 2016) [paper] [code]

  2. "Personalized page rank for named entity disambiguation" Maria Pershina, Yifan He, Ralph Grishman (NAACL 2015)[paper] [code]

  3. "Robust and Collective Entity Disambiguation through Semantic Embeddings Stefan" Stefan Zwicklbauer, Christin Seifert, Michael Granitzer (SIGIR 2016) [paper] [code]

maximization of CRF potentials

  1. "Deep joint entity disambiguation with local neural attention" Octavian-Eugen Ganea, Thomas Hofmann (EMNLP 2017) [paper] [code]

  2. "Improving entity linking by modeling latent relations between mentions" Phong Le, Ivan Titov (ACL 2018) [[paper]](./papers/Le, Titov - 2018 - Improving entity linking by modeling latent relations between mentions.pdf) [code]

sequential decision task

  1. "Joint Entity Linking with Deep Reinforcement Learning" Zheng Fang, Yanan Cao, Dongjie Zhang (2019) [paper] [code]

  2. "Learning dynamic context augmentation for global entity linking" Xiyuan Yang, Xiaotao Gu, Sheng Lin, Siliang Tang (EMNLP 2019) [paper] [code]

  3. "Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities" Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto (2019) [paper] [code]

neural model component

  1. "Neural Collective Entity Linking" Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu (COLING 2018)[paper] [code]

  2. "Collective entity resolution with multi-focal attention" Amir Globerson, Nevena Lazic, Soumen Chakrabarti (ACL 2016) [paper] [code]

  3. "End-to-end neural entity linking" Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann (CoNLL 2018) [paper] [code]

larger context

  1. "Bridging text and knowledge by learning multi-prototype entity mention embedding" Yixin Cao, Lifu Huang, Heng Ji, Xu Chen, Juanzi Li (ACL 2017) [paper] [code]

  2. "Entity linking via joint encoding of types, descriptions, and context" Nitish Gupta, Sameer Singh, Dan Roth (EMNLP 2017) [paper] [code]

  3. "Knowledge enhanced word representation" Matthew E. Peters, Mark Neumann, Robert Logan (EMNLP 2019) [paper] [code]

Domain Independent Architecture

distant learning

  1. "Distant learning for entity linking with automatic noise detection" Phong Le, Ivan Titov (ACL 2019) [paper] [code]

  2. "Boosting Entity Linking Performance by Leveraging Unlabeled Documents" Phong Le, Ivan Titov (ACL 2019) [paper] [code]

zero-shot

  1. "Learning dense representations for entity retrieval" Daniel Gillick, Sayali Kulkarni, Larry Lansing, (CoNLL 2019) [[paper]](./papers/Gillick et al. - 2019 - Learning dense representations for entity retrieval.pdf) [code]

  2. "Zero-shot entity linking by reading entity descriptions" Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee (ACL 2019) [paper] [code]

  3. "Scalable Zero-shot Entity Linking with Dense Entity Retrieval" Ledell Wu, Fabio Petroni, Martin Josifoski (EMNLP 2020) [paper] [code]

Cross-lingual Architecture

representation based

  1. "Cross-lingual Name Tagging and Linking for 282 Languages" Xiaoman Pan, Boliang Zhang, Jonathan May (ACL 2017) [paper] [code]

  2. "Cross-lingual Wikification Using Multilingual Embeddings" Chen-Tse Tsai, Dan Roth (NAACL 2016) [paper] [code]

zero-shot

  1. "Neural cross-lingual entity linking" Avirup Sil, Gourab Kundu, Radu Florian, Wael Hamza (AAAI 2018) [paper] [code]

  2. "Joint multilingual supervision for cross-lingual entity linking" Shyam Upadhyay, Nitish Gupta, Dan Roth ( EMNLP 2018) [paper] [code]

SOTA

AIDA-CoNLL

entity disambiguation

  1. "Entity-aware ELMo Learning Contextual Entity Representation for Entity Disambiguation" Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini, (2019) [paper] [code] [Accuracy: 0.962]

  2. "Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities" Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto (2019) [paper] [code] [Accuracy: 0.950]

  3. "Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models" Isaiah Onando Mulang’, Kuldeep Singh, Chaitali Prabhu (CIKM 2020) [paper] [code] [Accuracy: 0.9494]

  4. "DeepType Multilingual entity linking by neural type system evolution" Jonathan Raiman, Olivier Raiman (AAAI 2018) [paper] [code] [Accuracy: 0.909] [Accuracy: 0.9488]

  5. "Learning Distributed Representations of Texts and Entities from Knowledge Base" Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda (TACL 2017) [paper] [code] [Accuracy: 0.931]

entity linking

  1. "Autoregressive Entity Retrieval" Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni (2021) [paper] [code] [Micro-f1 strong: 0.837]

  2. "CHOLAN A modular approach for neural entity linking on wikipedia and wikidata" Manoj Prabhakar Kannan Ravi, Kuldeep Singh (EACL 2021) [paper] [code] [Micro-f1 strong: 0.831]

  3. "End-to-end neural entity linking" Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann (CoNLL 2018) [paper] [code] [Micro-f1 strong: 0.826]

  4. "Investigating entity knowledge in BERT with simple neural end-to-end entity linking" Samuel Broscheit (CoNLL 2019) [paper] [code] [Micro-f1 strong: 0.793]

TAC 2010

  1. "Scalable Zero-shot Entity Linking with Dense Entity Retrieval" Ledell Wu, Fabio Petroni, Martin Josifoski (EMNLP 2020) [paper] [code] [Accuracy: 0.940]

  2. "Neural Collective Entity Linking" Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu (COLING 2018)[paper] [code] [Accuracy: 0.910]

  3. "DeepType Multilingual entity linking by neural type system evolution" Jonathan Raiman, Olivier Raiman (AAAI 2018) [paper] [code] [Accuracy: 0.909]

  4. "ELDEN Improved entity linking using densified knowledge graphs" Priya Radhakrishnan, Partha Talukdar, Vasudeva Varma (NAACL 2018) [paper] [code] [Accuracy: 0.896]

  5. "Entity disambiguation by knowledge and text jointly embedding" Wei Fang, Jianwen Zhang, Dilin Wang, Zheng Chen, Ming Li (CoNLL 2016) [paper] [code] [Accuracy: 0.889]

ACE 2004

  1. "Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities" Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto (2019) [paper] [code] [Micro-f1: 0.919]

  2. "Entity linking via joint encoding of types, descriptions, and context" Nitish Gupta, Sameer Singh, Dan Roth (EMNLP 2017) [paper] [code]

  3. "Joint Entity Linking with Deep Reinforcement Learning" Zheng Fang, Yanan Cao, Dongjie Zhang (2019) [paper] [code] [Micro-f1: 0.912]

  4. "Autoregressive Entity Retrieval" Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni (2021) [paper] [code] [Micro-f1: 0.901]

  5. "Learning dynamic context augmentation for global entity linking" Xiyuan Yang, Xiaotao Gu, Sheng Lin, Siliang Tang (EMNLP 2019) [paper] [code] [Micro-f1: 0.901]

AQUAINT

  1. "Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities" Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto (2019) [paper] [code] [Micro-f1: 0.935]

  2. "Boosting Entity Linking Performance by Leveraging Unlabeled Documents" Phong Le, Ivan Titov (ACL 2019) [paper] [code] [Micro-f1: 0.907]

  3. "Autoregressive Entity Retrieval" Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni (2021) [[paper] [code] [Micro-f1: 0.899]

  4. "Deep joint entity disambiguation with local neural attention" Octavian-Eugen Ganea, Thomas Hofmann (EMNLP 2017) [paper] [code] [Micro-f1: 0.885]

  5. "Improving entity linking by modeling latent relations between mentions" Phong Le, Ivan Titov (ACL 2018) [[paper]](./papers/Le, Titov - 2018 - Improving entity linking by modeling latent relations between mentions.pdf) [code]

MSNBC

  1. "Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities" Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto (2019) [paper] [code] [Micro-f1: 0.963]

KILT

  1. "Autoregressive Entity Retrieval" Nicola De Cao, Gautier Izacard, Sebastian Riedel, Fabio Petroni (2021) [paper] [code]

  2. "Scalable Zero-shot Entity Linking with Dense Entity Retrieval" Ledell Wu, Fabio Petroni, Martin Josifoski (EMNLP 2020) [paper] [code]

  3. "KILT a Benchmark for Knowledge Intensive Language Tasks" Fabio Petroni, Aleksandra Piktus, Angela Fan (NAACL 2021) [paper] [code]

DuEL

  1. "Overview of the CCKS 2019 Knowledge Graph Evaluation Track Entity" Xianpei Han, Zhichun Wang, Jiangtao Zhang (CCKS 2019) [paper] [code]

Evaluation & Datasets

  1. "General entity annotator benchmarking framework" Ricardo Usbeck, Michael Röder (WWW 2015) [paper]

  2. "Robust disambiguation of named entities in text" Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bordino, (EMNLP 2011) [paper] AIDA

  3. "Overview of the TAC 2010 Knowledge Base Population Track" Heng Ji , Ralph Grishman , Hoa Trang Dang [paper] TAC KBP 2010

  4. "Large-Scale Named Entity Disambiguation Based on Wikipedia Data" Silviu Cucerzan (EMNLP 2007) [paper] MSNBC

  5. "Learning to link with wikipedia" David Milne, Ian H. Witten (CIKM 2008) [[paper]](./papers/Milne, Witten - 2008 - Learning to link with wikipedia.pdf) AQUAINT

  6. "Local and Global Algorithms for Disambiguation to Wikipedia" Lev Ratinov, Dan Roth, Doug Downey, Mike Anderson (ACL 2011)[paper] ACE2004

Comments

If you find any errors in the above information, please post it in Issues. Pull requests are welcomed for adding papers.

Comments

如果需要下载好的论文集，请在评论区留下邮箱地址📮

论文浅尝 | 通过阅读实体描述进行零样本的实体链接
开放知识图谱
04-02 647
笔记整理 |赖泽升，东南大学本科生来源：ACL2019动机先前实体链接的大多数工作都着重于与通用实体数据库的链接，通常希望链接到专门的实体词典，例如法律案件，公司项目描述，小说中的字...
必读论文|信息检索与推荐必读论文10篇
Arnetminer的博客
05-02 1706
AMiner研究团队开发出一款利用人工智能（AI）技术、帮助科研工作者阅读论文的智能论文搜索工具。该工具可以展示出该领域的必读论文，并且对所选论文进行“智能”阅读，反馈给你该论文的综述、研究方法及主要结论，即帮你快速阅读文献，大大地节省了时间和精力。 信息检索与推荐Topic必读论文 信息检索（Information Retrieval，IR）是指信息的表示、存储、组织和访问。信息推荐（Inf...
论文：Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions翻译笔记（实体链接与知识库： 问题、技术及解决方案）
最新发布
weixin_56242678的博客
03-24 917
论文：Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions翻译笔记（实体链接与知识库： 问题、技术及解决方案）
论文浅尝 | 基于多模态特征的视觉实体链接
开放知识图谱
01-07 1442
转载公众号 | 数据智能英文刊文章题目：Visual Entity Linking via Multi-modal Learning作者：郑秋硕，闻浩，王萌，漆桂林引用：Zheng, Q....
医疗实体链接（标准化）论文解读 （附代码） A Lightweight Neural Model for Biomedical Entity Linking
u010960155的博客
01-14 2559
一、动机 论文：https://arxiv.org/abs/2012.08844 代码：https://github.com/tigerchen52/Biomedical-Entity-Linking 医疗实体链接 (Biomedical Entity Linking) 把文档中发现的疾病、药物、手术名词（mention）映射到知识库（knowledge base）中的标准术语词。 这项任务其实是非常有挑战的，这是因为文档中出现的医疗词语存在着多种变化，比如缩写、同义词、词形态变化、词序、错
论文：Scalable Zero-shot Entity Linking with Dense Entity Retrieval翻译笔记（实体链接）
weixin_56242678的博客
03-24 1316
论文：Scalable Zero-shot Entity Linking with Dense Entity Retrieval翻译笔记（实体链接）
近期必读的【图神经网络（GNN）】相关论文-发表于WWW 2020.zip
03-31
这篇论文可能探讨了GNN在社交网络分析中的应用，如用户关系预测或者信息传播建模。GNN能够捕捉节点之间的复杂关系，从而更好地理解和预测网络行为。作者可能提出了新的GNN模型，改进了现有方法的性能，并通过实验...
原创 | 假期必读：一文看尽2019-2020各大顶会GNN论文（附链接）
数据派THU
01-20 2922
纵观2019年包括深度学习、计算机视觉、文本处理以及数据挖掘在内的顶级会议，图学习相关的论文较于之前都有十分明显的增长。而就 2020的情况来看，这个趋势还在不断扩大。总之，Graph ...
NLP相关书籍和论文综述
技术的点点滴滴
07-23 3310
1. An Introduction to Conditional Random Fields 本篇论文详细介绍了条件随机场（Conditional Random Fields，CRF）模型，了解CRF模型必读论文，包括有四个部分： 第一部分介绍了CRF模型的基础知识图模型，还有判别式模型和生成式模型的区别。 第二部分介绍了两种CRF模型，Linear-chain CRFs和General ...
自然语言经典的书籍
08-31
21. 指代消解与实体链接(Coreference Resolution and Entity Linking) - 如何确定文本中指代表达的真实指代对象。 22. 话语连贯性(Discourse Coherence) - 语篇分析中的连贯性概念及其在文本理解中的重要性。 23...
论文浅尝 | 基于潜在类别信息的实体链接
开放知识图谱
04-04 521
笔记整理 |黄一凡，东南大学本科生来源：AAAI2020链接：https://arxiv.org/pdf/2001.01447v1.pdf一、简介作者意识到在利用预训练模型进行实体链接时...
ccks2020中文短文本实体链接任务测评论文--小米团队--第一名
zzfive的博客
07-21 1581
ccks2020中文短文本实体链接任务测评论文--小米团队--第一名
整理了近五年顶会都收录了哪些实体链接文章
zenRRan的博客
02-09 828
每天给你送来NLP技术干货！来自：AI自然语言处理与知识图谱放假前看到了实体链接相关的一篇文章，节前已经给大家分享。开工了，也想花点时间着重看下近些年来实体链接这个任务目前的技术发展脉络，...
[NLP] 实体链接论文阅读—Entity Linking for Chinese Short Texts Based on BERT and Entity Name Embeddings
VIPsucks的博客
12-23 4101
Entity Linking for Chinese Short Texts Based on BERT and Entity Name Embeddings 写在前面： 最近在阅读实体链接论文，实体消歧是实体链接必须有的步骤，而实体链接的前一步为实体识别，对于只想知道本文到底用什么方法进行实体消歧并实体链接的，请直接移步第三部分Model架构的描述。这次直接用raw markdown写了，尝试过...
Neural Entity Linking综述【详细版】
Vincy_King
01-16 1499
NEL的最新详细综述~
实体链接中使用实体一致性信息（coherence）
u010960155的博客
05-27 2761
实体链接（Entity Linking; Entity Disambiguation）是自然语言处理中一个很重要的任务，目的是将文本中发现的mention链接到知识库（Knowledge Base）中的标注实体（Entity）。 实体链接一般需要考虑三种信息，先验信息（prior），mention和entity之间的相似度，实体之间的一致性（coherence） 先验信息。一个是实体本身出现的频率，一个是mention确定下链接到某实体的条件概率，即 p(e|m) 相似度。mention和
实体链指（1）Entity Linking 综述
小白的专栏
09-03 3271
实体链接（entity linking）任务是指识别出文本中的提及（mention）、确定mention的含义并消除其可能存在的歧义，然后建立该mention到 知识库（KB）中实体（entity）的链接，从而将非结构化数据连接到结构化数据的过程。
YAGO: A Core of Semantic Knowledge Unifying WordNet and Wikipedia
qq_39778575的博客
09-12 1003
梗概： Wikipedia中有大量的individuals，我们希望可以利用这些大量的实例，同时我们希望在一个知识库中concept可以按分类层次进行排列，但是Wikipedia的分类方式主要是基于主题，并不清晰，所以，我们需要将Wikipedia的实体与WordNet相结合。 在提取Wikipedia中的fact时，需要利用fact的category pages，并不访问page本身。这个category可以给我们很多信息，包括entity，relation，conc...
实体对齐论文
七月听雪的博客
11-22 887
实体对齐（实体链指 实体消歧）等主要是对预训练模型的微调。 微调主要包括预训练任务微调和输入表示微调，其中输入表示微调一般是先验知识的引入，预训练任务的调整主要是使模型契合实体相关的任务。 1.Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities https://arxiv.org/pdf/1909.00426v2.pdf 输入表示： 预训练任务：基于MLM的对.
AI入门：45篇必读论文推荐，跟上AI时代
论文列表包含了45篇精选论文，覆盖了从基础的神经网络到前沿的技术，如Transformer和BERT。此外，资源还提供了论文的下载方式，回复关键词"ai45"可获取。该列表还附带了一个包含原始PDF文件的压缩包和一个Zotero格式...
评论 15
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值