Details
| Original language | English |
|---|---|
| Pages (from-to) | 1543-1575 |
| Number of pages | 33 |
| Journal | Artificial intelligence review |
| Volume | 56 |
| Issue number | 2 |
| Publication status | Published - Feb 2023 |
| Externally published | Yes |
Abstract
In recent years some researchers have explored the use of reinforcement learning (RL) algorithms as key components in the solution of various natural language processing (NLP) tasks. For instance, some of these algorithms leveraging deep neural learning have found their way into conversational systems. This paper reviews the state of the art of RL methods for their possible use for different problems of NLP, focusing primarily on conversational systems, mainly due to their growing relevance. We provide detailed descriptions of the problems as well as discussions of why RL is well-suited to solve them. Also, we analyze the advantages and limitations of these methods. Finally, we elaborate on promising research directions in NLP that might benefit from RL.
Keywords
- Conversational systems, Natural language processing, Parsing, Reinforcement learning, Text generation, Translation
ASJC Scopus subject areas
- Arts and Humanities(all)
- Language and Linguistics
- Social Sciences(all)
- Linguistics and Language
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Artificial intelligence review, Vol. 56, No. 2, 02.2023, p. 1543-1575.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Survey on reinforcement learning for language processing
AU - Uc-Cetina, Víctor
AU - Navarro-Guerrero, Nicolás
AU - Martin-Gonzalez, Anabel
AU - Weber, Cornelius
AU - Wermter, Stefan
N1 - Publisher Copyright: © 2022, The Author(s).
PY - 2023/2
Y1 - 2023/2
N2 - In recent years some researchers have explored the use of reinforcement learning (RL) algorithms as key components in the solution of various natural language processing (NLP) tasks. For instance, some of these algorithms leveraging deep neural learning have found their way into conversational systems. This paper reviews the state of the art of RL methods for their possible use for different problems of NLP, focusing primarily on conversational systems, mainly due to their growing relevance. We provide detailed descriptions of the problems as well as discussions of why RL is well-suited to solve them. Also, we analyze the advantages and limitations of these methods. Finally, we elaborate on promising research directions in NLP that might benefit from RL.
AB - In recent years some researchers have explored the use of reinforcement learning (RL) algorithms as key components in the solution of various natural language processing (NLP) tasks. For instance, some of these algorithms leveraging deep neural learning have found their way into conversational systems. This paper reviews the state of the art of RL methods for their possible use for different problems of NLP, focusing primarily on conversational systems, mainly due to their growing relevance. We provide detailed descriptions of the problems as well as discussions of why RL is well-suited to solve them. Also, we analyze the advantages and limitations of these methods. Finally, we elaborate on promising research directions in NLP that might benefit from RL.
KW - Conversational systems
KW - Natural language processing
KW - Parsing
KW - Reinforcement learning
KW - Text generation
KW - Translation
UR - http://www.scopus.com/inward/record.url?scp=85131305728&partnerID=8YFLogxK
U2 - 10.1007/s10462-022-10205-5
DO - 10.1007/s10462-022-10205-5
M3 - Article
AN - SCOPUS:85131305728
VL - 56
SP - 1543
EP - 1575
JO - Artificial intelligence review
JF - Artificial intelligence review
SN - 0269-2821
IS - 2
ER -