Reasoning With Neural Tensor Networks for Knowledge Base Completion

By Richard Socher, Danqi Chen, Christopher D. Manning, Andrew Y. Ng. 2013

2,100 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

In Graph Learning

Citations in the corpus

SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (2018, background): “For instance, the negative examples could be incorrect relations in knowledge-base completion (Socher et al., 2013), or all words in a dictionary for a single-word cloze task (Zweig and Burges, 2011).”
Distributed Representations of Sentences and Documents (2014, methodology): “The results also show that more advanced methods (such as Recursive Neural Network (Socher et al., 2013b)), which require parsing and take into account the compositionality, perform much better.”
Ask Me Anything: Dynamic Memory Networks for Natural Language Processing (2015, methodology): “; classification problems like sentiment analysis (Socher et al., 2013) Copyright 2016 by the author(s).”
Neural Approaches to Conversational AI (2018, neutral): “. 3.3 Embedding-based Methods To address the paraphrasing problem, embedding-based methods map entities and relations in a KB to continuous vectors in a neural space; see, e.g., Bordes et al. (2013); Socher et al. (2013); Yang et al. (2015); Yih et al. (2015b). This space can be viewed as a hidden s”
Order-Embeddings of Images and Language (2015, methodology): “To apply order-embeddings to hypernymy, we follow the setup of Socher et al. (2013) in learning an N-dimensional vector for each concept in WordNet, but we replace their neural tensor network with our order-violation penalty deﬁned in Eq.”
Dynamic Memory Networks for Visual and Textual Question Answering (2016, methodology): “Neural approaches can include reasoning over knowledge bases, (Bordes et al., 2012; Socher et al., 2013a) or directly via sentences for trivia competitions (Iyyer et al., 2014).”
Knowledge Graph Embedding by Translating on Hyperplanes (2014, methodology): “…vary between simple difference (Bordes et al. 2012), translation (Bordes et al. 2013b), affine (Chang, Yih, and Meek 2013), general linear (Bordes et al. 2011), bilinear (Jenatton et al. 2012; Sutskever, Tenenbaum, and Salakhutdinov 2009), and nonlinear transformations (Socher et al. 2013).”
DKN: Deep Knowledge-Aware Network for News Recommendation (2018, methodology): “In addition to translation-based methods [4, 18, 26, 48] used in DKN, researchers have also proposed many other models such as Structured Embedding [5], Latent Factor Model [17], Neural Tensor Network [37] and GraphGAN [42].”
Learning Entity and Relation Embeddings for Knowledge Graph Completion (2015, methodology): “Since FB15K is generated by ourselves according to the strategy in (Socher et al. 2013), the evaluation results are not able to compare directly with those reported in (Wang et al.”
Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “For representation of more complex logical structures, i.e. ﬁrst order-logic formulas, a system named Logic Tensor Network (LTN) [42] is proposed by extending Neural Tensor Networks (NTN) [47], a state-of-the-art relational embedding method.”
Logic Tensor Networks for Semantic Image Interpretation (2017, background): “The grounding of an m-ary predicate P , namely G(P ), is defined as a generalization of the neural tensor network (which has been shown effective at knowledge completion in the presence of simple logical constraints [Socher et al., 2013]), as a function from R to [0, 1], as follows:”
Deep Learning: Methods and Applications (2014, methodology): “[347] developed the recursive neural tensor network, where each layer is constructed similarly to that of the neural tensor network described in [340] with an illustration shown in Figure 8.”
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, neutral): “SSP [59] ke s esk22 þ kek 2 2, Sðsh; stÞ 1⁄4 shþst kshþstk(2)2 NTN [131] ur tanhðhWrtþWrhhþWrttþ brÞ”
Modeling Relational Data with Graph Convolutional Networks (2017, methodology): “Most existing approaches to link prediction (for example, tensor and neural factorization methods [34, 23, 36, 40, 37]) can be interpreted under this framework.”
Complex Embeddings for Simple Link Prediction (2016, background): “However, dealing with anti-symmetric relations has so far almost always implied an explosion of the number of parameters (Nickel et al., 2011; Socher et al., 2013) (see Table 1), making models prone to overﬁtting.”