Encoding Prior Knowledge with Eigenword Embeddings
Explore this paper's citation graph
Summary
A way to incorporate prior knowledge into CCA is described, a theoretical justification for it is given, and it is tested by deriving word embeddings and evaluating them on a myriad of datasets.
- Type
- preprint
- Published
- 2015-09-03
- Cited by
- 27
- References
- 58
- Access
- Open access
- OpenAlex
- https://openalex.org/W1800542977
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11701649
Keywords
Word (group theory), Canonical correlation, Dimension (graph theory), Computer science, Context (archaeology)
References
- Generalization of CCA via Spectral Embedding
- Regularized Interlingual Projections: Evaluation on Multilingual Transliteration
- Improving Vector Space Word Representations Using Multilingual Correlation
- Visualization of labeled data using linear transformations
- Measuring Semantic Similarity in the Taxonomy of WordNet
- Efficient Estimation of Word Representations in Vector Space
- From Frequency to Meaning: Vector Space Models of Semantics
- SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation
- Incorporating Both Distributional and Relational Semantics in Word Representations
- ATM network: goals and challenges
- A word at a time: computing word relatedness using temporal semantic analysis
- Corpus-based Learning of Analogies and Semantic Relations
- Placing search in context: the concept revisited
- Contextual correlates of synonymy
- WordNet: A Lexical Database for English
- Three new graphical models for statistical language modelling
- Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
- Polarity Inducing Latent Semantic Analysis
- Contextual correlates of semantic similarity
- Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
Cited by
- Canonical Correlation Inference for Mapping Abstract Scenes to Text
- Semi-Supervised Learning of Sequence Models with Method of Moments
- Semantic-based Arabic Question Answering: Core and Recent Techniques
- Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
- Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules
- Specialising Word Vectors for Lexical Entailment
- Explicit Retrofitting of Distributional Word Vectors
- Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources
- Kernel and Moment Based Prediction and Planning : Applications to Robotics and Natural Language Processing
- Learning Word Vectors with Linear Constraints: A Matrix Factorization Approach
- Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
- Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization
- Leveraging Web Semantic Knowledge in Word Representation Learning
- Generalized Tuning of Distributional Word Vectors for Monolingual and Cross-Lingual Lexical Entailment
- Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
- Représentations vectorielles et apprentissage automatique pour l'alignement d'entités textuelles et de concepts d'ontologie: application à la biologie. (Vector Representations and Machine Learning for Alignment of Text Entities with Ontology Concepts: Application to Biology)
- Survey on the Use of Typological Information in Natural Language Processing
- A reproducible survey on word embeddings and ontology-based methods for word similarity: Linear combinations outperform the state of the art
- Specializing Distributional Vectors of All Words for Lexical Entailment
- Cross-lingual Semantic Specialization via Lexical Relation Induction
Related papers
- Understanding the Semantic Content of Sparse Word Embeddings Using a Commonsense Knowledge Base
- Utility of general and specific word embeddings for classifying translational stages of research
- Qualitative evaluation of word embeddings : investigating the instability in neural-based models
- Exploring the Combination of Contextual Word Embeddings and Knowledge Graph Embeddings
- On the Use of Word Embeddings Alone to Represent Natural Language Sequences
- Probabilistic Relation Induction in Vector Space Embeddings
- Enhancing Chinese Intent Classification by Dynamically Integrating Character Features into Word Embeddings with Ensemble Techniques
- How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks
- Investigating Word Meta-Embeddings by Disentangling Common and Individual Information