Jong-Hyeok Lee
Modeling Inter-Speaker Relationship in XLNet for Contextual Spoken Language Understanding
Access Model/Code and Paper
Transformer-based Automatic Post-Editing with a Context-Aware Encoding Approach for Multi-Source Inputs
Access Model/Code and Paper
Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding
Access Model/Code and Paper
Self-Attention-Based Message-Relevant Response Generation for Neural Conversation Model
Access Model/Code and Paper
Multiple Range-Restricted Bidirectional Gated Recurrent Units with Attention for Relation Classification
Access Model/Code and Paper
Improving Term Frequency Normalization for Multi-topical Documents, and Application to Language Modeling Approaches
* 8 pages, conference paper, published in ECIR '08
Access Model/Code and Paper
Unlimited Vocabulary Grapheme to Phoneme Conversion for Korean TTS
Access Model/Code and Paper
Integrating HMM-Based Speech Recognition With Direct Manipulation In A Multimodal Korean Natural Language Interface
Access Model/Code and Paper
Phonological modeling for continuous speech recognition in Korean
Access Model/Code and Paper
Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation
Access Model/Code and Paper
Integrated speech and morphological processing in a connectionist continuous speech understanding for Korean
Access Model/Code and Paper
Chart-driven Connectionist Categorial Parsing of Spoken Korean
Access Model/Code and Paper
TAKTAG: Two-phase learning method for hybrid statistical/rule-based part-of-speech disambiguation
Access Model/Code and Paper
SKOPE: A connectionist/symbolic architecture of spoken Korean processing
Access Model/Code and Paper
Bi-directional memory-based dialog translation: The KEMDT approach
Access Model/Code and Paper