Representations of Language Varieties Are Reliable Given Corpus Similarity Measures.
Jonathan DunnPublished in: CoRR (2021)
Keyphrases
- similarity measure
- programming language
- language learning
- spanish language
- parallel corpus
- natural language
- similarity function
- manually annotated
- similarity metrics
- machine learning
- cost effective
- higher level
- similarity measurement
- linguistic knowledge
- co occurrence
- description logics
- meaning representations
- open domain
- information retrieval
- similarity assessment
- text corpora
- test set
- computational linguistics
- semantic similarity
- neural network
- euclidean distance