Learning to Follow Directions with Untagged Data
Authors
Zhidan Yang, Zhiting Yang
Corresponding Author
Zhidan Yang
Available Online November 2017.
- DOI
- 10.2991/amms-17.2017.15How to use a DOI?
- Keywords
- component; untagged;lexicon; interpreter;program; semantic; directions; corpus
- Abstract
We describe a program learns to follow directions using a corpus, without human preprocessing. The program only build a semantic lexicon instead of semantic grammar to learn from an untagged corpus. Without grammar, the program uses a language-independent parser to find the boundaries between steps, then parse the steps. The rest of paper explains semantic interpreter and genetic algorithm.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Zhidan Yang AU - Zhiting Yang PY - 2017/11 DA - 2017/11 TI - Learning to Follow Directions with Untagged Data BT - Proceedings of the 2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2017) PB - Atlantis Press SP - 70 EP - 73 SN - 1951-6851 UR - https://doi.org/10.2991/amms-17.2017.15 DO - 10.2991/amms-17.2017.15 ID - Yang2017/11 ER -