Journal
NEUROCOMPUTING
Volume 477, Issue -, Pages 62-84Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2021.11.076
Keywords
Slavic languages; Task-oriented dialogue systems; Non-task-oriented dialogue systems; Chatbots; Machine learning; Artificial intelligence
Categories
Ask authors/readers for more resources
This article conducts an empirical study on the state-of-the-art dialogue systems within Slavic languages, reviews the existing models, and identifies the current main challenges and potential research directions for practical and intelligent systems within low-resourced languages.
Slavic languages pose a challenge to the researchers in the domain of dialogue technology. A relatively free word order with a large degree of inflection, such as conjugation of verbs, and declension of adjectives, pronouns, and nouns are exhibited by the Slavic languages, which has a significant impact on the size of lexical inventories that significantly complicate the design of dialogue systems. This article conducts an empirical study on the state-of-the-art dialogue systems within Slavic languages. Moreover, we review the existing models in recent dialogue systems, pinpoint the current main challenges and identify potential research directions of practical and intelligent systems within low-resourced languages. (C) 2021 Published by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available