Building Korean linguistic resource for NLU data generation of banking app CS dialog system

Jeongwoo Yoon (1, 2) , On-yu Park (1, 2) , Changhoe Hwang (1, 2) , Gwanghoon Yoo (1, 2) , Eric Laporte (3, 4) , Jeesun Nam (1, 2)

1 DICORA - Digital Language & Knowledge Contents Research Association
2 HUFS - Hankuk University of Foreign Studies
3 LIGM - Laboratoire d'Informatique Gaspard-Monge
4 Université Gustave Eiffel

Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increase the coverage of diverse utterances. In this study, we report the construction of a linguistic resource named FIAD (Financial Annotated Dataset) and its use to generate a Korean annotated training data for NLU in the banking customer service (CS) domain. By an empirical examination of a corpus of banking app reviews, we identified three linguistic patterns occurring in Korean request utterances: TOPIC (ENTITY, FEATURE), EVENT, and DISCOURSE MARKER. We represented them in LGGs (Local Grammar Graphs) to generate annotated data covering diverse intents and entities. To assess the practicality of the resource, we evaluate the performances of DIET-only (Intent: 0.91 /Topic [entity+feature]: 0.83), DIET+ HANBERT (I:0.94/T:0.85), DIET+ KoBERT (I:0.94/T:0.86), and DIET+ KorBERT (I:0.95/T:0.84) models trained on FIAD-generated data to extract various types of semantic items.

Mots clés: Natural language understanding; NLU; Dialog system; Annotated Dataset; Customer service; Banking service; Discourse marker; Local grammar graph; Deep learning; E-dictionary; Dictionary for language processing; Unitex; Sentence generation

Domaines: Informatique et langage [cs.CL]; Linguistique; Traitement du texte et du document

Jeongwoo Yoon, On-yu Park, Changhoe Hwang, Gwanghoon Yoo, Eric Laporte, et al.. Building Korean linguistic resource for NLU data generation of banking app CS dialog system. 29th International Conference on Computational Linguistics (COLING), Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning (Pan-DL), Oct 2022, Gyeongju, South Korea. pp.29-37. ⟨hal-03818541⟩