45 citations · 119 across the 23 of their papers we have counts for
23 papers
Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring
Heejin Do, Yunsu Kim, Gary Geunbae Lee
Automated essay scoring (AES) aims to score essays written for a given prompt, which defines the writing topic. Most existing AES systems assume to grade essays of the same prompt…
Score-balanced Loss for Multi-aspect Pronunciation Assessment
Heejin Do, Yunsu Kim, Gary Geunbae Lee
With rapid technological growth, automatic pronunciation assessment has transitioned toward systems that evaluate pronunciation in various aspects, such as fluency and stress. Howe…
DORIC : Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsing
Jihyun Lee, Seungyeon Seo, Yunsu Kim +1
We present our work on Track 2 in the Dialog System Technology Challenges 11 (DSTC11). DSTC11-Track2 aims to provide a benchmark for zero-shot, cross-domain, intent-set induction.…
Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking
Jihyun Lee, Chaebin Lee, Yunsu Kim +1
In dialogue state tracking (DST), labeling the dataset involves considerable human labor. We propose a new self-training framework for few-shot generative DST that utilize unlabele…
Hierarchical Pronunciation Assessment with Multi-Aspect Attention
Heejin Do, Yunsu Kim, Gary Geunbae Lee
Automatic pronunciation assessment is a major component of a computer-assisted pronunciation training system. To provide in-depth feedback, scoring pronunciation at various levels…
Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions
Seonjeong Hwang, Yunsu Kim, Gary Geunbae Lee
Conversational question answering (CQA) facilitates an incremental and interactive understanding of a given context, but building a CQA system is difficult for many domains due to…
Schema Encoding for Transferable Dialogue State Tracking
Hyunmin Jeon, Gary Geunbae Lee
Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require…
Conversational QA Dataset Generation with Answer Revision
Seonjeong Hwang, Gary Geunbae Lee
Conversational question--answer generation is a task that automatically generates a large-scale conversational question answering dataset based on input passages. In this paper, we…
SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
Jihyun Lee, Gary Geunbae Lee
Few-shot dialogue state tracking (DST) model tracks user requests in dialogue with reliable accuracy even with a small amount of data. In this paper, we introduce an ontology-free…
High Recall Data-to-text Generation with Progressive Edit
Choonghan Kim, Gary Geunbae Lee
Data-to-text (D2T) generation is the task of generating texts from structured inputs. We observed that when the same target sentence was repeated twice, Transformer (T5) based mode…
DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context
Hyunmin Jeon, Gary Geunbae Lee
Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, w…
Domain State Tracking for a Simplified Dialogue System
Hyunmin Jeon, Gary Geunbae Lee
Task-oriented dialogue systems aim to help users achieve their goals in specific domains. Recent neural dialogue systems use the entire dialogue history for abundant contextual inf…
Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems
Seonghan Ryu, Seokhwan Kim, Junhwi Choi +2
To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentence…
Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling
Byungsoo Kim, Hwanjo Yu, Gary Geunbae Lee
Previous studies in Open Information Extraction (Open IE) are mainly based on extraction patterns. They manually define patterns or automatically learn them from a large corpus. Ho…
Unlimited Vocabulary Grapheme to Phoneme Conversion for Korean TTS
Byeongchang Kim, WonIl Lee, Geunbae Lee +1
This paper describes a grapheme-to-phoneme conversion method using phoneme connectivity and CCV conversion rules. The method consists of mainly four modules including morpheme norm…
Integrating HMM-Based Speech Recognition With Direct Manipulation In A Multimodal Korean Natural Language Interface
Geunbae Lee, Jong-Hyeok Lee, Sangeok Kim
This paper presents a HMM-based speech recognition engine and its integration into direct manipulation interfaces for Korean document editor. Speech recognition can reduce typical…
Phonological modeling for continuous speech recognition in Korean
WonIl Lee, Geunbae Lee, Jong-Hyeok Lee
A new scheme to represent phonological changes during continuous speech recognition is suggested. A phonological tag coupled with its morphological tag is designed to represent the…
Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
Geunbae Lee, Jong-Hyeok Lee, JinHee Yoo
Most of the post-processing methods for character recognition rely on contextual information of character and word-fragment levels. However, due to linguistic characteristics of Ko…
Integrated speech and morphological processing in a connectionist continuous speech understanding for Korean
Geunbae Lee, Jong-Hyeok Lee
A new tightly coupled speech and natural language integration model is presented for a TDNN-based continuous possibly large vocabulary speech recognition system for Korean. Unlike…
TAKTAG: Two-phase learning method for hybrid statistical/rule-based part-of-speech disambiguation
Geunbae Lee, Jong-Hyeok Lee, Sanghyun Shin
Both statistical and rule-based approaches to part-of-speech (POS) disambiguation have their own advantages and limitations. Especially for Korean, the narrow windows provided by h…
SKOPE: A connectionist/symbolic architecture of spoken Korean processing
Geunbae Lee, Jong-Hyeok Lee
Spoken language processing requires speech and natural language integration. Moreover, spoken Korean calls for unique processing methodology due to its linguistic characteristics.…
Bi-directional memory-based dialog translation: The KEMDT approach
Geunbae Lee, Hanmin Jung, Jong-Hyeok Lee
A bi-directional Korean/English dialog translation system is designed and implemented using the memory-based translation technique. The system KEMDT (Korean/English Memory-based Di…
Phoneme-level speech and natural language intergration for agglutinative languages
Geunbae Lee Jong-Hyeok Lee Kyunghee Kim
A new tightly coupled speech and natural language integration model is presented for a TDNN-based large vocabulary continuous speech recognition system. Unlike the popular n-best t…