Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation

By Hongzhao Huang, Larry Heck, Heng Ji. 2015

93 citations recorded by the source corpus.

Entity Disambiguation aims to link mentions of ambiguous entities to a knowledge base (e.g., Wikipedia). Modeling topical coherence is crucial for this task based on the assumption that information from the same semantic context tends to belong to the same topic. This paper presents a novel deep semantic relatedness model (DSRM) based on deep neural networks (DNN) and semantic knowledge graphs (KGs) to measure entity semantic relatedness for topical coherence modeling. The DSRM is directly trained on large-scale KGs and it maps heterogeneous types of knowledge of an entity from KGs to numerical feature vectors in a latent space such that the distance between two semantically-related entities is minimized. Compared with the state-of-the-art relatedness approach proposed by (Milne and Witten, 2008a), the DSRM obtains 19.4% and 24.5% reductions in entity disambiguation errors on two publicly available datasets respectively.

Subfields: Artificial Intelligence, Management Science and Operations Research, Natural Language Processing, Graph Learning

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 Management Science and Operations Research

In Natural Language Processing

In Graph Learning

Citations in the corpus

Autoregressive Entity Retrieval (2020, methodology): “Although there has been extensive previous work on entity retrieval (e.g. Hoffart et al., 2011; Pic-cinno & Ferragina, 2014; Huang et al., 2015; Le & Titov, 2018; Logeswaran et al., 2019; Broscheit, 2019; Wu et al., 2019, to name just a few) there is a common design choice to most current…”
Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “tion [146], semantic analysis [147], [148], information retrieval [149], [150], entity recognition [151], [152], relation extraction [153], [154], [155], [156], and event detection [157], [158].”
Deep Joint Entity Disambiguation with Local Neural Attention (2017, background): “We note that the best result on this dataset was reported in the unpublished work of (Huang et al., 2015).”
Collective Entity Disambiguation with Structured Gradient Tree Boosting (2018, unknown): “PPRforNED In-KB acc. et al. (2015) 86.4 Huang et al. (2015) 86.6 Chisholm and Hachey (2015) 88.7 Ganea et al. (2016) 87.6 Guo and Barbosa (2016) 89.0 Globerson et al. (2016) 91.0 Yamada et al. (2016) 91.5 Ganea and Hofmann (2017) 92.2”
Deep Learning for Entity Matching: A Design Space Exploration (2018, methodology): “[35] rely on the knowledge base structure and develop a deep, semantic entity similarity model using feed-forward NNs.”
Text feature extraction based on deep learning: a review (2017, background): “…analysis [48], question answering [49 – 52], machine translation [53 – 56], text classification [57], summarization [58, 59], and text generation [60], as well as information extraction, including named entity recognition [61, 62], relation extraction [63 – 67], and event detection [68 – 70].”
Neural Network Matrix Factorization (2015, methodology): “Other approaches to KGs use neural networks to produce representations, rather than map representations to predictions, like NTN and NNMF. (See, e.g., (Huang et al., 2015) and (Bian et al., 2014).)”
Joint Entity Linking with Deep Reinforcement Learning (2019, methodology): “obal LSTM network, the number of LSTM cell units is 700 and the batch size is 16. In the above two LSTM networks, Table 2: In-KB accuracy result on AIDA-B dataset. Methods AIDA-B Huang and Heck (2015)[21] 86.6% Chisholm and Hachey (2015)[6] 88.7% Guo and Barbosa (2016)[16] 89.0% Globerson et al. (20”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “The trendy end-to-end learning approaches have made efforts through representation learning of entities and mentions, for example, DSRM [95] for modeling entity semantic relatedness and EDKate [96] for the joint embedding of entity and text.”
Improving Entity Linking by Modeling Latent Relations between Mentions (2018, background): “The coherence score function, in the simplest form, is a sum over all pairwise scores (cid:8)( e i ; e j ; D ) (Ratinov et al., 2011; Huang et al., 2015; Chisholm and Hachey, 2015; Ganea et al., 2016; Guo and Barbosa, 2016; Globerson et al., 2016; Yamada et al., 2016), resulting in: (cid:8)( e i ;…”