Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction
Explore this paper's citation graph
Summary
This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information from the text and from existing knowledge, based on scoring functions that operate by learning low-dimensional embeddings of words, entities and relationships from a knowledge base.
- Type
- article
- Published
- 2013-07-30
- Cited by
- 251
- References
- 27
- Access
- Open access
- OpenAlex
- https://openalex.org/W1792926363
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:89639
Keywords
Relationship extraction, Relation (database), Computer science, Embedding, Natural language processing
References
- Multi-instance Multi-label Learning for Relation Extraction
- A Three-Way Model for Collective Learning on Multi-Relational Data
- Toward an Architecture for Never-Ending Language Learning
- Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing
- A Joint Model of Language and Perception for Grounded Attribute Learning
- Reading The Web with Learned Syntactic-Semantic Inference Rules
- Constructing Biological Knowledge Bases by Extracting Information from Text Sources
- Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling
- Large scale image annotation: learning to rank with joint word-image embeddings
- Distant supervision for relation extraction without labeled data
- Learning Language Semantics from Ambiguous Supervision
- Irreflexive and Hierarchical Relations as Translations
- Learning Semantic Correspondences with Less Supervision
- Translating Embeddings for Modeling Multi-relational Data
- Open Information Extraction from the Web
- Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations
- Autonomously semantifying wikipedia
- Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences
- Learning Structured Embeddings of Knowledge Bases
- Open Information Extraction Using Wikipedia
Cited by
- Universal Schema for Knowledge Representation from Text and Structured Data
- Knowledge-based question answering using the semantic embedding space
- Modeling Relation Paths for Representation Learning of Knowledge Bases
- Knowledge base completion by learning pairwise-interaction differentiated embeddings
- Bias Modeling for Distantly Supervised Relation Extraction
- Probabilistic Belief Embedding for Knowledge Base Completion
- Book Reviews: Semantic Relations Between Nominals by Vivi Nastase, Preslav Nakov, Diarmuid Ó Séaghdha, and Stan Szpakowicz
- A Primer on Neural Network Models for Natural Language Processing
- Component-Enhanced Chinese Character Embeddings
- Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding
- KNET: A General Framework for Learning Word Embedding Using Morphological Knowledge
- Evolutionary fine-tuning of automated semantic annotation systems
- Relational Path Mining in Structured Knowledge
- Typed Tensor Decomposition of Knowledge Bases for Relation Extraction
- #TagSpace: Semantic Embeddings from Hashtags
- Queries as a Source of Lexicalized Commonsense Knowledge
- RC-NET: A General Framework for Incorporating Knowledge into Word Representations
- Translating Embeddings for Modeling Multi-relational Data
- Knowledge Graph and Text Jointly Embedding
- Transition-based Knowledge Graph Embedding with Relational Mapping Properties
Related papers
- Global Relation Embedding for Relation Extraction
- Language Model Pre-training Method in Machine Translation Based on Named Entity Recognition
- A neural network framework for relation extraction: Learning entity semantic and relation pattern
- A Chinese-English parallel corpus for information extraction
- Investigations on Knowledge Base Embedding for Relation Prediction and Extraction
- Relation Extraction with Contextualized Relation Embedding
- A relation aware embedding mechanism for relation extraction
- Exploring Sentence Embedding Structures for Semantic Relation Extraction