ISSN:2149-9225

CODING MOLD WORDS ON DIALOGUE BOT


Human beings think, make decisions and communicate through the words they know. The connection of the human beings to the world occurs through their native language. The words of Wittgenstein who says "The boundaries of my language are the boundaries of my world" shows that language is not merely a system of vocal signs. As a person establishes a bond with the world, he expresses feelings such as happiness, sadness and hurt in word patterns. Formulaic Expression, which are among these patterns, enable to express thoughts laconically just like proverbs, idioms, conflates and hendiadys. Stereotyped sayings such as good morning, congratulations, goodbye, good afternoon, I'm fine, I hope nothing's wrong, good appetite and farewell enable people to express themselves comfortably, to communicate thoughts briefly and clearly in good or bad moments, to regulate social mechanisms and comply with common courtesy, to be able to understand speakers plainly within a short time, to express cultural and religious values by connecting with society with a sense of belonging, and to eliminate confusion in communication. It is important to make the online interactive Turkish dialogue bot Gökbilge use the features and functions of stereotyped sayings, which have an important frequency of occurrence in spoken language and therefore encode them into its database. While the selection and dissection of stereotyped sayings were carried out mainly through the study of Gökdayı (2011), Gökbilge's responses towards the stereotyped sayings used by the speakers were generated through the questionnaires conducted with these speakers and sample conversations were prepared in order to show the context-oriented functions of stereotyped sayings through the chatbot. Thanks to the database that was generated, the dialogue bot Gökbilge knows many stereotyped sayings in the Turkish language and is able to use them in a context-oriented way. The aforementioned database of Gökbilge can provide data to many studies with its aspect of being an assistant bot that can be used in areas such as conversation exams, native language education and foreign language education.


Keywords


Keywords: Turkish, Stereotyped Sayings, Conversation, Natural Language Processing, Dialogue Bot.

Author : Yeşim MUTLU
Number of pages: 261-288
DOI: http://dx.doi.org/10.29228/kesit.42210
Full text:
Paylaş:
Kesit Akademi
E-Mail Subscription

By subscribing to E-Newsletter, you can get the latest news to your e-mail.