Neural-based Text Error Correction (TEC) System

A Neural-based Text Error Correction (TEC) System is a TEC system that implements a neural TEC algorithm to solve a neural TEC task (to produce a neural TEC model).

• Context:
  • It can range from being a Character-Level Neural TEC System to being a Word/Token-level Neural TEC System.
• Example(s):
  • a Convolutional Encoder/Decoder-based GEC System such as:
    • mlconvgec2018 [1] (Chollampatt & Ng, 2018);
  • a Fairseq-based one.
  • a Deep Learning Based Spelling System such as:
  • a DeepSpell [2].
  • an Error-Correcting Output Coded NLM (ECOC-NLM) System (Neill & Bollegala , 2019).
  • …
• Counter-Example(s):
  • a Maximum Likelihood-based Text Error Correction (TEC) System.
  • a Parsing System,
• See: GEC System, Text Error Detection System, Language Model-based TEC System, Neural Language Model, Artificial Neural Network, Deep Learning System, Natural Language Processing System.

---

---

References

2019

• (Neill & Bollegala, 2019) ⇒ James O' Neill, and Danushka Bollegala. (2019). “Error-Correcting Neural Sequence Prediction.”

2018a

• (GitHub, 2018) ⇒ https://github.com/nusnlp/mlconvgec2018
  • QUOTE: Code and model files for the paper: “A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction” (In AAAI-18).

2018b

• (Chollampatt & Ng, 2018) ⇒ Shamil Chollampatt, and Hwee Tou Ng. (2018). “A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction.” In: Proceedings of the Thirty-Second Conference on Artificial Intelligence (AAAI-2018).
  • QUOTE: We improve automatic automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network.

---