R-grams: Unsupervised Learning of Semantic Units in Natural Language
arXiv:1808.04670
Abstract
This paper investigates data-driven segmentation using Re-Pair or Byte Pair Encoding-techniques. In contrast to previous work which has primarily been focused on subword units for machine translation, we are interested in the general properties of such segments above the word level. We call these segments r-grams, and discuss their properties and the effect they have on the token frequency distribution. The proposed approach is evaluated by demonstrating its viability in embedding techniques, both in monolingual and multilingual test settings. We also provide a number of qualitative examples of the proposed methodology, demonstrating its viability as a language-invariant segmentation procedure.
References in corpus (5)
- Distributed Representations of Words and Phrases and their Compositionality
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- From Frequency to Meaning: Vector Space Models of Semantics
- Character-Aware Neural Language Models
- Non Sequential Recursive Pair Substitution: Some Rigorous Results