R-grams: Unsupervised Learning of Semantic Units in Natural Language
This work addresses language-invariant segmentation for NLP applications, but it appears incremental as it builds on existing techniques like Re-Pair or BPE.
The paper tackles the problem of data-driven segmentation above the word level in natural language, introducing r-grams and showing their viability in embedding techniques across monolingual and multilingual settings.
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.