Learning Entity Representation for Entity Disambiguation

By Zhengyan He, Shujie Liu, Mu Li, Ming Zhou, Longkai Zhang, Houfeng Wang. 2013

165 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

In Information Extraction

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, neutral): “Like He et al. (2013), they use it to score entries from an alias table rather than directly for retrieval.”
Zero-shot Entity Linking with Dense Entity Retrieval (2019, neutral): “For candidate ranking, He et al. (2013), Sun et al.”
Deep Joint Entity Disambiguation with Local Neural Attention (2017, methodology): “For instance (Francis-Landau et al., 2016; He et al., 2013) use convolutional neural networks (CNNs) and stacked denoising auto-encoders, respectively, to learn representations of textual documents and canonical entity pages.”
Deep Neural Architectures for Joint Named Entity Recognition and Disambiguation (2019, background): “[2] are the first to use deep neural networks in ED task.”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, background): “(He et al. 2013) investigate Stacked Denoising Auto-encoders to learn entity representation.”
Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation (2019, methodology): “There are several limitations with the existing local models (He et al., 2013; Sun et al., 2015; Hu et al., 2015; Yamada et al., 2016, 2017; Ganea and Hofmann, 2017; Sil et al., 2018; Le and Titov, 2018) in capturing contextual dependencies between mention and candiadate entities.”
Named Entity Disambiguation for Noisy Text (2017, methodology): “The ﬁrst neural approach for NED (He et al., 2013) used stacked auto-encoders to learn a similarity measure between mention-context structures and entity candidates.”
End-to-End Neural Entity Linking (2018, methodology): “In the context of ED, recent neural methods (He et al., 2013; Sun et al., 2015; Yamada et al., 2016; Ganea and Hofmann, 2017; Le and Titov, 2018; Yang et al., 2018; Radhakrishnan et al., 2018) have established state-of-the-art results, outperforming engineered features based models.”
Fine-Grained Entity Typing for Domain Independent Entity Linking (2019, methodology): “Recent approaches have used neural techniques (He et al., 2013; Sun et al., 2015; Francis-Landau et al., 2016), various joint models (Durrett and Klein, 2014; Nguyen et al.”
Entity Linking via Joint Encoding of Types, Descriptions, and Context (2017, methodology): “, using feedforward networks on bag-of-words of the entity context (He et al., 2013), or using entity-class information from KB (Sun et al.”
Collective Entity Resolution with Multi-Focal Attention (2016, background): “Personalized PageRank (PPR) (Jeh and Widom, 2003) is another tractable alternative, adopted by several recent systems (Han and Sun, 2011; He et al., 2013; Alhelbawy and Gaizauskas, 2014; Pershina et al., 2015).”
Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation (2016, methodology): “(He et al., 2013) used deep neural networks to compute representations of entities and contexts of mentions directly from the KB.”
Improving Language Understanding by Generative Pre-Training (2018, methodology): “In recent work, the method has been used to help train deep neural networks on various tasks like image classification [69], speech recognition [68], entity disambiguation [17] and machine translation [48].”
Modeling Mention, Context and Entity with Neural Networks for Entity Disambiguation (2015, methodology): “The semantic representation of text can be effectively used as features for a variety of NLP tasks, including machine translation [Cho et al., 2014], syntactic parsing [Socher et al., 2013a], discourse parsing [Li et al., 2014], relation classification [Zeng et al., 2014], sentiment analysis [Socher”
Improving Entity Linking by Modeling Latent Relations between Mentions (2018, unknown): “These approaches rely on pretrained embed-dings of words (Mikolov et al., 2013; Penning-ton et al., 2014) and entities (He et al., 2013; Ya-mada et al., 2017; Ganea and Hofmann, 2017) and often do not use virtually any other hand-crafted features.”
Learning Dynamic Context Augmentation for Global Entity Linking (2019, background): “, 2015) or dense embeddings (He et al., 2013; Nguyen et al., 2016; Francis-Landau et al., 2016), play key roles in distinguishing different candidates.”
Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, background): “[105] proposed a deep learning technique [106] to automatically learn the context-entity similarity measure for entity linking based on the assumption that the correct mapping entity should be more similar to the context of the entity mention than any other candidate entity.”
Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation (2015, background): “…et al., 2003; Mnih and Hin-ton, 2007; Hinton and Salakhutdinov, 2010; Col-lobert et al., 2011; Bordes et al., 2012; Huang et al., 2012; Bordes et al., 2013; Socher et al., 2013; Mikolov et al., 2013; He et al., 2013; Huang et al., 2013; Shen et al., 2014; Yih et al., 2014; Gao et al., 2014)).”
Neural Cross-Lingual Entity Linking (2017, result): “Noting that the entire document D might not be useful for disambiguating m , we choose to represent the mention m based only on the surrounding sentences of m in D , in contrast to (He et al. 2013; Francis-Landau, Durrett, and Klein 2016), which chose to use the entire document for modeling.”