Search Results for author: Myeong Cheol Shin

Found 6 papers, 2 papers with code

OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection with Natural Language Attack

1 code implementation12 May 2021 DongHyun Choi, Myeong Cheol Shin, EungGyun Kim, Dong Ryeol Shin

Out-of-domain (OOD) input detection is vital in a task-oriented dialogue system since the acceptance of unsupported inputs could lead to an incorrect response of the system.

intent-classification Intent Classification +1

Auxiliary Sequence Labeling Tasks for Disfluency Detection

no code implementations24 Oct 2020 Dongyub Lee, Byeongil Ko, Myeong Cheol Shin, Taesun Whang, Daniel Lee, Eun Hwa Kim, EungGyun Kim, Jaechoon Jo

Existing works for disfluency detection have focused on designing a single objective only for disfluency detection, while auxiliary objectives utilizing linguistic information of a word such as named entity or part-of-speech information can be effective.

named-entity-recognition Named Entity Recognition +4

RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

1 code implementation CL (ACL) 2021 DongHyun Choi, Myeong Cheol Shin, EungGyun Kim, Dong Ryeol Shin

Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given.

Ranked #7 on Text-To-SQL on spider (Exact Match Accuracy (Test) metric)

Position slot-filling +2

Cannot find the paper you are looking for? You can Submit a new open access paper.