6 papers
Bridging the Training-Inference Gap for Dense Phrase Retrieval
Gyuwan Kim, Jinhyuk Lee, Barlas Oguz +4
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these proced…
Large Product Key Memory for Pretrained Language Models
Gyuwan Kim, Tae-Hwan Jung
Product key memory (PKM) proposed by Lample et al. (2019) enables to improve prediction accuracy by increasing model capacity efficiently with insignificant computational overhead.…
ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding
Minjeong Kim, Gyuwan Kim, Sang-Woo Lee +1
Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT…
Efficient Dialogue State Tracking by Selectively Overwriting Memory
Sungdong Kim, Sohee Yang, Gyuwan Kim +1
Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches…
Subword Language Model for Query Auto-Completion
Gyuwan Kim
Current neural query auto-completion (QAC) systems rely on character-level language models, but they slow down when queries are long. We present how to utilize subword language mod…
Extended Abstract: Mimicry Resilient Program Behavior Modeling with LSTM based Branch Models
Hayoon Yi, Gyuwan Kim, Jangho Lee +4
In the software design, protecting a computer system from a plethora of software attacks or malware in the wild has been increasingly important. One branch of research to detect th…