Relation Extraction with Matrix Factorization and Universal Schemas

By Sebastian Riedel, Limin Yao, Andrew McCallum, Benjamin M. Marlin. 2013

692 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

Zero-Shot Relation Extraction via Reading Comprehension (2017, background): “Universal schema (Riedel et al., 2013) represents open IE extractions and knowledge-base facts in a single matrix, whose rows are entity pairs and columns are relations.”
KILT: a Benchmark for Knowledge Intensive Language Tasks (2020, background): “Likewise, while the classical approach of information extraction for populating a Knowledge Base (KB, Riedel et al., 2013; Surdeanu and Ji, 2014) seems out-of-fashion, recent results show that they remain contenders (Fan et al., 2019a; Xiong et al., 2019).”
Word Representations via Gaussian Embedding (2014, background): “Given the parallels between embedding models and matrix factorization (Deerwester et al., 1990; Riedel et al., 2013; Levy & Goldberg, 2014), this is relevant to our approach.”
Multi-Relational Latent Semantic Analysis (2013, background): “In addition, the information in different slices can come from heterogeneous sources (conceptually similar to (Riedel et al., 2013)), which not only improves the model, but also extends the word coverage in a reliable way.”
Modeling Relational Data with Graph Convolutional Networks (2017, background): “Beyond modeling knowledge bases, R-GCNs can be generalized to other applications where relation factorization models have been shown effective (e.g. relation extraction).”
Sentence Embedding Alignment for Lifelong Relation Extraction (2019, methodology): “As an essential component for structured information extraction, it has been widely used in downstream tasks such as automatic knowledgebased completion (Riedel et al., 2013) and question answering (Yih et al.”
Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “The conventional RE methods (Riedel et al., 2013; Zeng et al., 2014; Lin et al., 2016) mostly focus on recognizing relations for a ﬁxed pre-deﬁned relation set, and cannot handle rapidly emerging novel relations in the real world.”
Matching the Blanks: Distributional Similarity for Relation Learning (2019, methodology): “Following Riedel et al. (2013), we assume access to a corpus of text in which entities have been linked to unique identiﬁers and we deﬁne a rela-a tion statement to be a block of text containing two marked entities.”
Injecting Logical Background Knowledge into Embeddings for Relation Extraction (2015, methodology): “Second, in the spirit of OpenIE, a universal schema can use textual patterns as novel relations and thus increases the coverage of traditional schemas (Riedel et al., 2013; Fan et al., 2014).”
Complex Embeddings for Simple Link Prediction (2016, background): “For example, the Universal Schema approach (Riedel et al., 2013) factorizes a 2D un-folding of the tensor (a matrix of entity pairs vs. relations) while Welbl et al. (2016) extend this also to other pairs.”
Open Question Answering with Weakly Supervised Embedding Models (2014, background): “Initial works attempting to learn to connect KBs and natural language with less supervision have actually been tackling the information extraction problem [16,11,14,19].”
Commonsense Knowledge Base Completion (2016, methodology): “Our methods are similar to past work on KBC (Mintz et al., 2009; Nickel et al., 2011; Lao et al., 2011; Nickel et al., 2012; Riedel et al., 2013; Gardner et al., 2014; West et al., 2014), particularly methods based on distributed representations and neural networks (Socher et al., 2013; Bordes et…”
A Review of Relational Machine Learning for Knowledge Graphs (2015, background): “Furthermore, [85] considered learning latent representations for the argument slots in a relation to learn the correct types from data.”
A Neural Knowledge Language Model (2016, background): “Because the knowledge graphs such as Freebase are usually incomplete in the sense that some facts are missing or incorrect, there have been also many works on the knowledge-base completion [33, 35, 38].”
Representing Text for Joint Embedding of Text and Knowledge Bases (2015, methodology): “We directly build on the universal schema approach of Riedel et al. (2013) as well as the universal schema extension of the D IST M ULT model mentioned previously, to improve the representations of textual relations by capturing their compositional structure.”
NaturalLI: Natural Logic Inference for Common Sense Reasoning (2014, background): “Yao et al. (2012) and Riedel et al. (2013) present a related line of work, inferring new relations between Freebase entities via inference over both Freebase and OpenIE relations.”
Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge (2020, background): “This idea has also been extended with works looking at ways of incorporating raw text and symbolic KGs into a shared embedding space (Riedel et al., 2013; Verga et al., 2016), to be jointly reasoned over (Sun et al.”
Traversing Knowledge Graphs in Vector Space (2015, background): “An elegant solution to incompleteness is using vector space representations: Controlling the dimensionality of the vector space forces generalization to new facts (Nickel et al., 2011; Nickel et al., 2012; Socher et al., 2013; Riedel et al., 2013; Nee-lakantan et al., 2015).”