91 citations · 137 across the 13 of their papers we have counts for
9 papers · 1 filter
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…
Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation
Soyoung Yoon, Sungjoon Park, Gyuwan Kim +5
Research on Korean grammatical error correction (GEC) is limited, compared to other major languages such as English. We attribute this problematic circumstance to the lack of a car…
Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length
Shira Guskin, Moshe Wasserblat, Ke Ding +1
Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. TinyBERT addresses the computational efficiency…
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…
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
Gyuwan Kim, Kyunghyun Cho
Despite transformers' impressive accuracy, their computational cost is often prohibitive to use with limited computational resources. Most previous approaches to improve inference…
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…
Training IBM Watson using Automatically Generated Question-Answer Pairs
Jangho Lee, Gyuwan Kim, Jaeyoon Yoo +3
IBM Watson is a cognitive computing system capable of question answering in natural languages. It is believed that IBM Watson can understand large corpora and answer relevant quest…