Neural Natural Language Generation (NLG) Algorithm
A Neural Natural Language Generation (NLG) Algorithm is a NLG algorithm that is a neural NLP algorithm.
- Context:
- It can be implemented by a Neural NLG System (that solves a neural NLG task).
- …
- Counter-Example(s):
- Counter-Example(s):
- See: OpenAI GPT-2.
References
2020
- (Karpukhin et al., 2020) ⇒ Vladimir Karpukhin, Barlas Oguz, Seo Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. (2020). "Dense Passage Retrieval for Open-Domain Question Answering." In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 6769-6781).
2019
- https://blog.usejournal.com/generating-natural-language-text-with-neural-networks-e983bb48caad
- QUOTE: ... the field of AI has recently developed a method that can both encode representations of our world to a space of meanings (proto-read) and can transcribe points in that meaning space into language (proto-write). The method uses neural networks, so we call it neural text generation.
The figure above depicts neural text generation. The world state is a representation, such as an image or written sentence. The encoder is a neural network that maps the representation into a meaning space. This meaning space is a space of vectors, like the popular word vectors. These vectors are long sequences of numbers, and the space is like the familiar two-dimensional space with x and y coordinates, with the exception that there are hundreds of coordinates instead of just two. The decoders are neural networks, and there can be multiple decoders, each capable of writing a version of the meaning in a particular language or style. ...
- QUOTE: ... the field of AI has recently developed a method that can both encode representations of our world to a space of meanings (proto-read) and can transcribe points in that meaning space into language (proto-write). The method uses neural networks, so we call it neural text generation.