Modeling Mention, Context and Entity with Neural Networks for Entity Disambiguation

By Yaming Sun, Lei Lin, Duyu Tang, Nan Yang, Z. Ji, Xiaolong Wang. 2015

196 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, methodology): “Sun et al. (2015) also use a dual encoder that has similar structure to ours.”
Zero-shot Entity Linking with Dense Entity Retrieval (2019, methodology): “Following prior work (Sun et al., 2015; Cao et al., 2018; Gillick et al., 2019), we pre-train our models on Wikipedia 4 data.”
Deep Joint Entity Disambiguation with Local Neural Attention (2017, methodology): “In a similar local setting (Sun et al., 2015) embed mentions, their immediate contexts and their candidate entities using word embeddings and CNNs.”
Scalable Zero-shot Entity Linking with Dense Entity Retrieval (2019, methodology): “Following prior work (Sun et al., 2015; Cao et al., 2018; Gillick et al., 2019; Onoe and Durrett, 2019), we pre-train our models on Wikipedia6 data.”
Deep Learning for Entity Matching: A Design Space Exploration (2018, background): “For example, recent DL work [21, 74] proposed the use of hierarchical word embeddings to obtain representations that capture entity cooccurrences, Ganea et al.”
Learning Cross-Context Entity Representations from Text (2020, methodology): “There is signiﬁcant previous work that makes use of neural context and entity encoders in downstream entity linking systems (Sun et al., 2015; Yamada et al., 2016; 2017; Gupta et al., 2017; Murty et al., 2018; Kolitsas et al., 2018), but that previous work focuses solely on discriminating between…”
Effective LSTMs for Target-Dependent Sentiment Classification (2015, methodology): “We obtain target vector vtarget by averaging the vectors of words it contains, which has been proven to be simple and effective in representing named entities (Socher et al., 2013a; Sun et al., 2015).”
Target-Dependent Sentiment Classification with Long Short Term Memory (2015, methodology): “We obtain target vector v target by averaging the vectors of words it contains, which has been proven to be simple and effective in representing named entities [Socher et al., 2013a; Sun et al., 2015].”
Entity Linking via Joint Encoding of Types, Descriptions, and Context (2017, methodology): “…modules (Ling et al., 2015), simple classifiers (Cucerzan, 2007; Ratinov et al., 2011), graphical models (Durrett and Klein, 2014), classifiers augmented with ILP inference (Cheng and Roth, 2013), and more recently, neural approaches (He et al., 2013; Sun et al., 2015; Francis-Landau et al., 2016).”
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.”
Aspect Level Sentiment Classification with Deep Memory Network (2016, background): “For the case where aspect is multi word expression like “battery life”, aspect representation is an average of its constituting word vectors (Sun et al., 2015).”
Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation (2019, methodology): “For AIDA-CoNLL, the existing literature has considered two different candidate sets: (aida-Yago), which is extracted and used by (Ganea and Hofmann, 2017; Le and Titov, 2018) and (aida-HP): a less ambiguous one extracted by (Pershina et al., 2015).”
Joint Learning of Named Entity Recognition and Entity Linking (2019, methodology): “EL state-of-the-art methods often correspond to local methods which use as main features a candidate entity representation, a mention representation, and a representation of the mention’s context (Sun et al., 2015; Yamada et al., 2016, 2017; Ganea and Hofmann, 2017).”
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.”
Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks (2016, background): “, 2015) and for capturing similarity in models for entity linking (Sun et al., 2015) and other related tasks (Dong et al.”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, methodology): “Comparing CoAtt with the method (Sun et al. 2015) which is trained over one million Wikipedia anchor texts, our method CoAtt achieves comparable performance even trained with less training data.”
Named Entity Disambiguation for Noisy Text (2017, methodology): “While convolutional neural networks (Sun et al., 2015; Francis-Landau et al., 2016) and probabilistic attention (Lazic et al., 2015) have been applied to the task, this is the ﬁrst model to use RNNs and a neural attention model for NED.”