Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks

By Matthew Francis-Landau, Greg Durrett, Daniel Klein. 2016

181 citations recorded by the source corpus.

A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention's context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to achieve state-of-the-art performance on multiple entity linking datasets, outperforming the prior systems of Durrett and Klein (2014) and Nguyen et al. (2014).

Subfields: Artificial Intelligence, Natural Language Processing, 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 Artificial Intelligence

In Natural Language Processing

In Information Extraction

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, neutral): “Most recent work on entity resolution has focused on training neural network models for the candidate reranking stage (Francis-Landau et al., 2016; Eshel et al., 2017; Yamada et al., 2017a; Gupta et al., 2017; Sil et al., 2018).”
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.”
Neural Cross-Lingual Entity Linking (2017, methodology): “ ablation study, we notice that adding the LDC layer provides a boost to our model in both the datasets, Systems In-KB acc. % Hoffart et al. (2011) 82.5 Gupta et al. (2017) 82.9 He et al. (2013) 85.6 Francis-Landau et al. (2016) 85.5 Sil & Florian (2016) 86.2 Lazic et al. (2015) 86.4 Chisholm &a”
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries (2020, background): “, 2011), neural EL (Francis-Landau et al., 2016; Kolitsas et al., 2018) Entity embeddings Text, entity mention spans Entity embeddings Joint embedding of entities and text (Yamada et al.”
Stacking With Auxiliary Features (2016, methodology): “For ImageNet object detection in 2015, the top performing team used a deep residual net [He et al. , 2015] and several other teams deployed a version of faster R-CNN (Region based Convolutional Neural Networks) with selective search [ Ren et al. , 2015 ] .”
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.”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, methodology): “From the table, we can see that even without the attention mechanism and the type information, the simple method LSTM-AVG outperforms FL-Single, which illustrates that our encoding method based on biLSTM is more effective in modeling mention contexts and entity descriptions.”
Dense Text Retrieval Based on Pretrained Language Models: A Survey (2022, unknown): “models for effective candidate ranking [334]–[336].”
Learning Dynamic Context Augmentation for Global Entity Linking (2019, methodology): “We apply the DCA process in two popular local models with different styles: the first is a neural attention model named ETHZ-Attn (Ganea and Hofmann, 2017), the other is the BerkeleyCNN (Francis-Landau et al., 2016) model which is made up of multiple convolutional neural networks (CNN).”
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.”
Entity Linking via Joint Encoding of Types, Descriptions, and Context (2017, methodology): “Berkeley-CNN (Francis-Landau et al., 2016), that uses CNNs operating over different granularity of entity and mention contexts, also follows this training regime and trains separate models for each dataset.”
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.”