29 citations · 60 across the 13 of their papers we have counts for
15 papers
False Negative Distillation and Contrastive Learning for Personalized Outfit Recommendation
Seongjae Kim, Jinseok Seol, Holim Lim +1
Personalized outfit recommendation has recently been in the spotlight with the rapid growth of the online fashion industry. However, recommending outfits has two significant challe…
Self-Guided Contrastive Learning for BERT Sentence Representations
Taeuk Kim, Kang Min Yoo, Sang-goo Lee
Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we…
Contrastive Learning for Unsupervised Image-to-Image Translation
Hanbit Lee, Jinseok Seol, Sang-goo Lee
Image-to-image translation aims to learn a mapping between different groups of visually distinguishable images. While recent methods have shown impressive ability to change even in…
Masked Contrastive Learning for Anomaly Detection
Hyunsoo Cho, Jinseok Seol, Sang-goo Lee
Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to al…
Semantics-Preserving Adversarial Training
Wonseok Lee, Hanbit Lee, Sang-goo Lee
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this pape…
Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models
Taeuk Kim, Bowen Li, Sang-goo Lee
As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to devel…
SNU_IDS at SemEval-2019 Task 3: Addressing Training-Test Class Distribution Mismatch in Conversational Classification
Sanghwan Bae, Jihun Choi, Sang-goo Lee
We present several techniques to tackle the mismatch in class distributions between training and test data in the Contextual Emotion Detection task of SemEval 2019, by extending th…
Data Augmentation for Spoken Language Understanding via Joint Variational Generation
Kang Min Yoo, Youhyun Shin, Sang-goo Lee
Data scarcity is one of the main obstacles of domain adaptation in spoken language understanding (SLU) due to the high cost of creating manually tagged SLU datasets. Recent works i…
Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
Taeuk Kim, Jihun Choi, Daniel Edmiston +2
Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We pres…
Cell-aware Stacked LSTMs for Modeling Sentences
Jihun Choi, Taeuk Kim, Sang-goo Lee
We propose a method of stacking multiple long short-term memory (LSTM) layers for modeling sentences. In contrast to the conventional stacked LSTMs where only hidden states are fed…
SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension
Taeuk Kim, Jihun Choi, Sang-goo Lee
We present a novel neural architecture for the Argument Reasoning Comprehension task of SemEval 2018. It is a simple neural network consisting of three parts, collectively judging…
Improving Visually Grounded Sentence Representations with Self-Attention
Kang Min Yoo, Youhyun Shin, Sang-goo Lee
Sentence representation models trained only on language could potentially suffer from the grounding problem. Recent work has shown promising results in improving the qualities of s…
Style2Vec: Representation Learning for Fashion Items from Style Sets
Hanbit Lee, Jinseok Seol, Sang-goo Lee
With the rapid growth of online fashion market, demand for effective fashion recommendation systems has never been greater. In fashion recommendation, the ability to find items tha…
A Syllable-based Technique for Word Embeddings of Korean Words
Sanghyuk Choi, Taeuk Kim, Jinseok Seol +1
Word embedding has become a fundamental component to many NLP tasks such as named entity recognition and machine translation. However, popular models that learn such embeddings are…
Learning to Compose Task-Specific Tree Structures
Jihun Choi, Kang Min Yoo, Sang-goo Lee
For years, recursive neural networks (RvNNs) have been shown to be suitable for representing text into fixed-length vectors and achieved good performance on several natural languag…