Discrete Word Embedding for Logical Natural Language Understanding
arXiv:2008.11649
Abstract
We propose an unsupervised neural model for learning a discrete embedding of words. Unlike existing discrete embeddings, our binary embedding supports vector arithmetic operations similar to continuous embeddings. Our embedding represents each word as a set of propositional statements describing a transition rule in classical/STRIPS planning formalism. This makes the embedding directly compatible with symbolic, state of the art classical planning solvers.
arXiv commentequal contribution
References in corpus (18)
- Efficient Estimation of Word Representations in Vector Space
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distributed Representations of Words and Phrases and their Compositionality
- Auto-Encoding Variational Bayes
- Categorical Reparameterization with Gumbel-Softmax
- Using Information Content to Evaluate Semantic Similarity in a Taxonomy
- Semantics derived automatically from language corpora contain human-like biases
- The FF Planning System: Fast Plan Generation Through Heuristic Search
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Learning Plannable Representations with Causal InfoGAN
- Measuring Word Significance using Distributed Representations of Words
- Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
- An Exploration of Word Embedding Initialization in Deep-Learning Tasks
- Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
- Controlled Experiments for Word Embeddings
- LSTM-Based Goal Recognition in Latent Space
- Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder