Search Results for author:
Found 38 papers, 17 papers with code
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge a gap between external knowledge and LLM's parametric knowledge.
Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection
Based on the findings, we further train the classifier with the dataset augmented by FAILOpt prompt.
Aligning Language Models to Explicitly Handle Ambiguity
In interactions between users and language model agents, user utterances frequently exhibit ellipsis (omission of words or phrases) or imprecision (lack of exactness) to prioritize efficiency.
Proxy-based Item Representation for Attribute and Context-aware Recommendation
Additionally, that the proxy embeddings are shared across all items allows the infrequent items to borrow training signals of frequent items in a unified model structure and end-to-end manner.
Ranked #1 on
Recommendation Systems
on Amazon Fashion
(using extra training data)
Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP
When deploying machine learning systems to the wild, it is highly desirable for them to effectively leverage prior knowledge to the unfamiliar domain while also firing alarms to anomalous inputs.
CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels
Additionally, our proposed methodology can be applied universally to any LM and has the potential to scale to larger models, making it a more viable option for utilizing large LMs.
Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning
As the size of the pre-trained language model (PLM) continues to increase, numerous parameter-efficient transfer learning methods have been proposed recently to compensate for the tremendous cost of fine-tuning.
Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners
Through in-context learning (ICL), large-scale language models are effective few-shot learners without additional model fine-tuning.
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble
Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience.
Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator
Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream task.
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations
Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive.
Exploiting Session Information in BERT-based Session-aware Sequential Recommendation
In recommendation systems, utilizing the user interaction history as sequential information has resulted in great performance improvement.
Technologies for AI-Driven Fashion Social Networking Service with E-Commerce
The rapid growth of the online fashion market brought demands for innovative fashion services and commerce platforms.
False Negative Distillation and Contrastive Learning for Personalized Outfit Recommendation
The first challenge is that outfit recommendation often requires a complex and large model that utilizes visual information, incurring huge memory and time costs.
Self-Guided Contrastive Learning for BERT Sentence Representations
In this work, we propose a contrastive learning method that utilizes self-guidance for improving the quality of BERT sentence representations.
Masked Contrastive Learning for Anomaly Detection
However, the primary objective of contrastive learning is to learn task-agnostic features without any labels, which is not entirely suited to discern anomalies.
Contrastive Learning for Unsupervised Image-to-Image Translation
Image-to-image translation aims to learn a mapping between different groups of visually distinguishable images.
Semantics-Preserving Adversarial Training
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data.
IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize?
We propose a novel method that enables us to determine words that deserve to be emphasized from written text in visual media, relying only on the information from the self-attention distributions of pre-trained language models (PLMs).
Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models
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 develop a method for extracting complete (binary) parses from PLMs without training separate parsers.
Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction
With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings.
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation
Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks.
Summary Level Training of Sentence Rewriting for Abstractive Summarization
As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary.
Ranked #5 on
Extractive Text Summarization
on CNN / Daily Mail
Abstractive Text Summarization
Extractive Text Summarization
+3
Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
We propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i. e. Hanja).
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching
We present a latent variable model for predicting the relationship between a pair of text sequences.
SNU IDS at SemEval-2019 Task 3: Addressing Training-Test Class Distribution Mismatch in Conversational Classification
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 the existing methods for class imbalance problem.
Ranked #6 on
Emotion Recognition in Conversation
on EC
SNU_IDS at SemEval-2019 Task 3: Addressing Training-Test Class Distribution Mismatch in Conversational Classification
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 the existing methods for class imbalance problem.
Cell-aware Stacked LSTMs for Modeling Sentences
We propose a method of stacking multiple long short-term memory (LSTM) layers for modeling sentences.
Ranked #10 on
Sentiment Analysis
on SST-5 Fine-grained classification
Data Augmentation for Spoken Language Understanding via Joint Variational Generation
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.
Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
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.
Element-wise Bilinear Interaction for Sentence Matching
When we build a neural network model predicting the relationship between two sentences, the most general and intuitive approach is to use a Siamese architecture, where the sentence vectors obtained from a shared encoder is given as input to a classifier.
SNU\_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension
We present a novel neural architecture for the Argument Reasoning Comprehension task of SemEval 2018.
SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension
We present a novel neural architecture for the Argument Reasoning Comprehension task of SemEval 2018.
Improving Visually Grounded Sentence Representations with Self-Attention
Sentence representation models trained only on language could potentially suffer from the grounding problem.
Supersense Tagging with a Combination of Character, Subword, and Word-level Representations
Recently, there has been increased interest in utilizing characters or subwords for natural language processing (NLP) tasks.
Style2Vec: Representation Learning for Fashion Items from Style Sets
With the rapid growth of online fashion market, demand for effective fashion recommendation systems has never been greater.
A Syllable-based Technique for Word Embeddings of Korean Words
Word embedding has become a fundamental component to many NLP tasks such as named entity recognition and machine translation.
Learning to Compose Task-Specific Tree Structures
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 language processing tasks.
Ranked #58 on
Natural Language Inference
on SNLI
