Explicit Retrofitting of Distributional Word Vectors
Explore this paper's citation graph
Summary
This work transforms external lexico-semantic relations into training examples which are used to learn an explicit retrofitting model (ER), which allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well.
- Type
- article
- Published
- 2018-01-01
- Cited by
- 77
- References
- 61
- Access
- Open access
- OpenAlex
- https://openalex.org/W2798962680
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:51867127
Keywords
Retrofitting, Computer science, Word (group theory), Natural language processing, Distributional semantics
References
- Symmetric Pattern Based Word Embeddings for Improved Word Similarity Prediction
- Polyglot: Distributed Word Representations for Multilingual NLP
- Improving Distributional Similarity with Lessons Learned from Word Embeddings
- Encoding Prior Knowledge with Eigenword Embeddings
- SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation
- Computing Lexical Contrast
- Cognitive User Interfaces
- Placing search in context: the concept revisited
- Polarity Inducing Latent Semantic Analysis
- Multimodal Distributional Semantics
- The Berkeley FrameNet Project
- BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network
- RC-NET: A General Framework for Incorporating Knowledge into Word Representations
- AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes
- Exploiting Similarities among Languages for Machine Translation
- Word Semantic Representations using Bayesian Probabilistic Tensor Factorization
- Distributed Representations of Words and Phrases and their Compositionality
- Eigenwords: spectral word embeddings
- Morphological Inflection Generation Using Character Sequence to Sequence Learning
- The Role of Context Types and Dimensionality in Learning Word Embeddings
Cited by
- A Survey of Cross-lingual Word Embedding Models
- Expansional Retrofitting for Word Vector Enrichment
- Leveraging Web Semantic Knowledge in Word Representation Learning
- Attention-based long short-term memory network using sentiment lexicon embedding for aspect-level sentiment analysis in Korean
- Imparting interpretability to word embeddings while preserving semantic structure
- What just happened? Evaluating retrofitted distributional word vectors
- Generalized Tuning of Distributional Word Vectors for Monolingual and Cross-Lingual Lexical Entailment
- Multilingual and Cross-Lingual Graded Lexical Entailment
- Unsupervised Cross-Lingual Representation Learning
- Specializing Distributional Vectors of All Words for Lexical Entailment
- Metaphors in Text Simplification: To change or not to change, that is the question
- Cross-lingual Semantic Specialization via Lexical Relation Induction
- Retrofitting Contextualized Word Embeddings with Paraphrases
- Informing Unsupervised Pretraining with External Linguistic Knowledge
- A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces
- Interactive Refinement of Cross-Lingual Word Embeddings
- Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization
- Learning Conceptual-Contextual Embeddings for Medical Text
- Understanding the Semantic Content of Sparse Word Embeddings Using a Commonsense Knowledge Base
- Offline versus Online Representation Learning of Documents Using External Knowledge
Related papers
- Analysis of The Characteristics of Similar Words Computed by Word Embeddings
- Distributional Measures of Semantic Distance: A Survey
- Network-based distributional semantic models
- Dictionary-based Debiasing of Pre-trained Word Embeddings
- A critique of word similarity as a method for evaluating distributional semantic models
- Evaluation of taxonomic and neural embedding methods for calculating semantic similarity
- Explaining human performance in psycholinguistic tasks with models of semantic similarity based on prediction and counting : A review and empirical validation