Relation Schema Induction using Tensor Factorization with Side Information

@inproceedings{Nimishakavi2016RelationSI,
  title={Relation Schema Induction using Tensor Factorization with Side Information},
  author={Madhav Nimishakavi and Uday Singh Saini and Partha P. Talukdar},
  booktitle={EMNLP},
  year={2016}
}
Given a set of documents from a specific domain (e.g., medical research journals), how do we automatically build a Knowledge Graph (KG) for that domain? Automatic identification of relations and their schemas, i.e., type signature of arguments of relations (e.g., undergo(Patient, Surgery)), is an important first step towards this goal. We refer to this problem as Relation Schema Induction (RSI). In this paper, we propose Schema Induction using Coupled Tensor Factorization (SICTF), a novel… Expand
Higher-order Relation Schema Induction using Tensor Factorization with Back-off and Aggregation
TLDR
This paper proposes Tensor Factorization with Back-off and Aggregation (TFBA), a novel framework for the HRSI problem and is the first attempt at inducing higher-order relation schemata from unlabeled text. Expand
Knowledge Completion for Generics using Guided Tensor Factorization
TLDR
This work considers the problem of inferring additional such facts about common nouns or generics at a precision similar to that of the starting KB, and presents the first approach that is successful. Expand
Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference
TLDR
This paper analyzes the varied performance of Matrix Factorization on the related tasks of relation extraction and knowledge-base completion and proposes three extensions to MF, including a TF-augmented MF model that is robust and obtains strong results across various KBI datasets. Expand
Semi-Supervised Tensor Factorization for Node Classification in Complex Social Networks
TLDR
This paper extends RESCAL to produce a semi-supervised factorization method that combines a classification error term with the standard factor optimization process, and models the tensorial data assimilating observed information from all the relations, while also taking into account classification performance. Expand
Neural Graph Embedding Methods for Natural Language Processing
TLDR
GCNs are utilized for Document Timestamping problem and for learning word embeddings using dependency context of a word instead of sequential context and two limitations of existing GCN models are addressed. Expand
Joint Matrix-Tensor Factorization for Knowledge Base Inference
TLDR
An extensive evaluation to compare popular KB inference models across popular datasets in the literature and proposes an extension to MF models so that they can better handle out-of-vocabulary (OOV) entity pairs, and develops a novel combination of TF and MF models. Expand
CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information
TLDR
Canonicalization using Embeddings and Side Information (CESI) is proposed -- a novel approach which performs canonicalization over learned embeddings of Open KBs by incorporating relevant NP and relation phrase side information in a principled manner. Expand
OKGIT: Open Knowledge Graph Link Prediction with Implicit Types
TLDR
This work proposes OKGIT that improves OpenKG link prediction using novel type compatibility score and type regularization and shows that the proposed method achieves state-of-the-art performance while producing type compatible NPs in the link prediction task. Expand
Inductive Framework for Multi-Aspect Streaming Tensor Completion with Side Information
TLDR
A dynamic tensor completion framework called Side Information infused Incremental Tensor Analysis (SIITA), which incorporates side information and works for general incremental tensors and how non-negative constraints can be incorporated with SIITA is shown. Expand
Sampo: Unsupervised Knowledge Base Construction for Opinions and Implications
TLDR
This work proposes an unsupervised KBC system, SAMPO, that is tailored to build KBs for domains where many reviews on the same domain are available and shows that KBs generated using SAMPO can provide additional training data to fine-tune language models used for downstream tasks such as review comprehension. Expand
...
1
2
...

References

SHOWING 1-10 OF 42 REFERENCES
Towards Combined Matrix and Tensor Factorization for Universal Schema Relation Extraction
TLDR
Two hybrid methods that combine the benefits of tensor and matrix factorization are investigated, showing that the combination can be fruitful and handle ambiguously phrased relations, achieve gains in accuracy on real-world relations, and demonstrate that entity embeddings encode entity types. Expand
Discovering facts with boolean tensor tucker decomposition
TLDR
This paper proposes the use of Boolean Tucker tensor decomposition to simultaneously find the entity and relation synonyms and the facts connecting them from the raw triples, and shows that the method obtains high precision while the low recall can easily be remedied by considering the original data together with the decomposition. Expand
Relation Extraction with Matrix Factorization and Universal Schemas
TLDR
This work presents matrix factorization models that learn latent feature vectors for entity tuples and relations that achieve substantially higher accuracy than a traditional classification approach and is able to reason about unstructured and structured data in mutually-supporting ways. Expand
Typed Tensor Decomposition of Knowledge Bases for Relation Extraction
TLDR
A tensor decomposition approach for knowledge base embedding that is highly scalable, and is especially suitable for relation extraction by leveraging relational domain knowledge about entity type information, which is significantly faster than previous approaches and better able to discover new relations missing from the database. Expand
KB-LDA: Jointly Learning a Knowledge Base of Hierarchy, Relations, and Facts
TLDR
This work proposes an unsupervised model that jointly learns a latent ontological structure of an input corpus, and identifies facts from the corpus that match the learned structure. Expand
Factorizing YAGO: scalable machine learning for linked data
TLDR
This work presents an efficient approach to relational learning on LOD data, based on the factorization of a sparse tensor that scales to data consisting of millions of entities, hundreds of relations and billions of known facts, and shows how ontological knowledge can be incorporated in the factorizations to improve learning results and how computation can be distributed across multiple nodes. Expand
Rubik: Knowledge Guided Tensor Factorization and Completion for Health Data Analytics
TLDR
This work proposes Rubik, a constrained non-negative tensor factorization and completion method for phenotyping that can discover more meaningful and distinct phenotypes than the baselines and can also discover sub-phenotypes for several major diseases. Expand
A Three-Way Model for Collective Learning on Multi-Relational Data
TLDR
This work presents a novel approach to relational learning based on the factorization of a three-way tensor that is able to perform collective learning via the latent components of the model and provide an efficient algorithm to compute the factorizations. Expand
Knowledge vault: a web-scale approach to probabilistic knowledge fusion
TLDR
The Knowledge Vault is a Web-scale probabilistic knowledge base that combines extractions from Web content (obtained via analysis of text, tabular data, page structure, and human annotations) with prior knowledge derived from existing knowledge repositories that computes calibrated probabilities of fact correctness. Expand
Discovering Relations between Noun Categories
TLDR
This work proposes an approach to automatically discovering relevant relations, given a large text corpus plus an initial ontology defining hundreds of noun categories, and concludes this is a useful approach to semi-automatic extension of the ontology for large-scale information extraction systems such as NELL. Expand
...
1
2
3
4
5
...