Subword Embedding System

A Subword Embedding System is a text item embedding system that implements a subword embedding algorithm to solve a subword embedding task (to map a subword unit into a vector representation).

• AKA: Subword Representation System.
• Context:
  • It can be based on a Language Modeling System and Feature Learning System.
  • …
• Example(s):
  • Character Embedding System,
  • SentencePiece Embedding System.
  • …
• Counter-Example(s):
  • Word Embedding System,
  • Morpheme Embedding System,
  • Phrase Embedding System.
• See: Byte-Pair Encoding (BPE) Subword Segmentation Algorithm, Distributional-based Subword Embedding Space, Sequence Embedding System, Natural Language Processing System, Word Detection System, Language Model, POS Tagging System.

---

---

References

2018

• (Kudo & Richardson, 2018) ⇒ Taku Kudo, and John Richardson. (2018). “SentencePiece: A Simple and Language Independent Subword Tokenizer and Detokenizer for Neural Text Processing". In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) System Demonstrations. DOI:10.18653/v1/d18-2012.

2016

• (Sennrich et al., 2016) ⇒ Rico Sennrich, Barry Haddow, and Alexandra Birch. (2016). “Neural Machine Translation of Rare Words with Subword Units.” In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-2016).

---