Structured Relation Discovery using Generative Models

By Limin Yao, Aria Haghighi, Sebastian Riedel, Andrew McCallum. 2011

178 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.

Citations in the corpus

Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation (2022, neutral): “…supervised (Ze-119 lenko et al., 2002; Liu et al., 2013; Zeng et al., 2014;120 Miwa and Bansal, 2016), semi-supervised (Chen121 et al., 2006; Sun et al., 2011; Hu et al., 2020) and122 distantly supervised methods (Mintz et al., 2009;123 Yao et al., 2011; Zeng et al., 2015; Han et al.,124 2018a).”
Curriculum-Meta Learning for Order-Robust Continual Relation Extraction (2021, neutral): “2019), and distantly supervised methods (Yao et al. 2011; Marcheggiani and Titov 2016).”
Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020, background): “…Corro and Gemulla, 2013; Angeli et al., 2015; Petroni et al., 2015; Stanovsky and Da-gan, 2016; Mausam, 2016; Cui et al., 2018), relation discovery (Yao et al., 2011; Marcheggiani and Titov, 2016), relation clustering (Shinyama and Sekine, 2006; Elsahar et al., 2017; Wu et al., 2019), and data…”
Injecting Logical Background Knowledge into Embeddings for Relation Extraction (2015, background): “First, for canonical relations it effectively performs distant supervision (Bunescu and Mooney, 2007; Mintz et al., 2009; Yao et al., 2011; Hoffmann et al., 2011; Surdeanu et al., 2012) and hence requires no textual annotations.”
Neural Snowball for Few-Shot Relation Learning (2019, background): “Other work exploits the way to form relation types automatically by clustering semantic patterns of given data (Lin and Pantel, 2001; Shinyama and Sekine, 2006; Yao et al., 2011; Marcheggiani and Titov, 2016; ElSahar et al., 2017).”
Relation Extraction Using Distant Supervision (2018, methodology): “The authors of [71] propose a series of generative probabilistic models in that context.”
T-REx: A Large Scale Alignment of Natural Language with Knowledge Base Triples (2018, result): “Previous works [Mintz et al.2009,Yao et al.2011] have created alignments either manually or automatically for the purpose of training and evaluating their models.”
An Unsupervised Text Mining Method for Relation Extraction from Biomedical Literature (2014, background): “These approaches are quite powerful but have very high computational requirements [18].”
Learning Latent Personas of Film Characters (2013, background): “This work also naturally draws on earlier work on the unsupervised learning of verbal arguments and semantic roles (Pereira et al., 1993; Grenager and Manning, 2006; Titov and Klementiev, 2012) and unsupervised relation discovery (Yao et al., 2011).”
Rule-Based Information Extraction is Dead! Long Live Rule-Based Information Extraction Systems! (2013, background): “Authors hid rules behind euphemisms such as “de-pendency restrictions” (Mausam et al., 2012), “en-tity type constraints” (Yao et al., 2011), or “seed dic-tionaries” (Putthividhya and Hu, 2011).”
Pattern Learning for Relation Extraction with a Hierarchical Topic Model (2012, background): “…, a semi-supervised procedure consisting of ﬁnding sentences that contain two entities whose relation we know, and using those sentences as training examples for a supervised classiﬁer (Hoffmann et al., 2010; Wu and Weld, 2010; Hoffmann et al., 2011; Wang et al., 2011; Yao et al., 2011).”
Relation Extraction with Matrix Factorization and Universal Schemas (2013, methodology): “We Surface form clustering models correlations between patterns, and can be fed into RE (Yao et al., 2011).”
Open domain event extraction from twitter (2012, methodology): “We adopt an approach based on latent variable models inspired by recent work on modeling selectional preferences [47, 39, 22, 52, 48], and unsupervised information extraction [4, 55, 7].”
CORE: Context-Aware Open Relation Extraction with Factorization Machines (2015, background): “…KB and surface relations is to cluster the relations: whenever two relations appear in the same cluster, they are treated as synonymous (Hasegawa et al., 2004; Shinyama and Sekine, 2006; Yao et al., 2011; Takamatsu et al., 2011; Min et al., 2012; Akbik et al., 2012; de Lacalle and La-pata, 2013).”
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, background): “Yao et al. (2011); Marcheggiani and Titov (2016) propose to use generative models and treat these relations as latent variables, while Shinyama and Sekine (2006); El-sahar et al. (2017); Wu et al. (2019) cast relation discovery as a clustering task.”
Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations (2016, methodology): “2We define triggers as in Yao et al. (2011), namely “all the words on the dependency path except stop words”.”
Typed Tensor Decomposition of Knowledge Bases for Relation Extraction (2014, result): “We compare the proposed T RESCAL model to RI13 (Riedel et al., 2013), YA11 (Yao et al., 2011), MI09 (Mintz et al., 2009) and SU12 (Surdeanu et al., 2012) 8 .”
Quantifying Similarity between Relations with Fact Distribution (2019, background): “Recently, some efforts are devoted to Open Relation Extraction (Open RE) (Lin and Pantel, 2001; Yao et al., 2011; Marcheggiani and Titov, 2016; ElSahar et al., 2017), aiming to cluster relation patterns into several relation types instead of redundant relation patterns.”