Search Results for author:
Found 29 papers, 5 papers with code
Have You Seen That Number? Investigating Extrapolation in Question Answering Models
Our work rigorously tests state-of-the-art models on DROP, a numerical MRC dataset, to see if they can handle passages that contain out-of-range numbers.
Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering
Numerical reasoning over text is a challenging subtask in question answering (QA) that requires both the understanding of texts and numbers.
HyperCLOVA X Technical Report
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding.
A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting
Time series forecasting is one of the most essential and ubiquitous tasks in many business problems, including demand forecasting and logistics optimization.
Direct Preference-based Policy Optimization without Reward Modeling
We apply our algorithm to offline RL tasks with actual human preference labels and show that our algorithm outperforms or is on par with the existing PbRL methods.
Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning
Recent studies have proposed unified user modeling frameworks that leverage user behavior data from various applications.
Ask Me What You Need: Product Retrieval using Knowledge from GPT-3
In this paper, we propose a GPT-3 based product retrieval system that leverages the knowledge-base (KB) of GPT-3 for question answering; users do not need to know the specific illustrative keywords for a product when querying.
Deformable Graph Transformer
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision.
VQ-AR: Vector Quantized Autoregressive Probabilistic Time Series Forecasting
Time series models aim for accurate predictions of the future given the past, where the forecasts are used for important downstream tasks like business decision making.
Hazard Gradient Penalty for Survival Analysis
Our method applies to any survival analysis model including the ODE modeling framework and is easy to implement.
Metropolis-Hastings Data Augmentation for Graph Neural Networks
We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.
Scaling Law for Recommendation Models: Towards General-purpose User Representations
Here we explore the possibility of general-purpose user representation learning by training a universal user encoder at large scales.
Intent-based Product Collections for E-commerce using Pretrained Language Models
In this paper, we use a pretrained language model (PLM) that leverages textual attributes of web-scale products to make intent-based product collections.
Assumption-Free Survival Analysis Under Local Smoothness Prior
Survival analysis appears in various fields such as medicine, economics, engineering, and business.
Know Your Action Set: Learning Action Relations for Reinforcement Learning
Intelligent agents can solve tasks in a variety of ways depending on the action set at their disposal.
Global-Local Item Embedding for Temporal Set Prediction
Temporal set prediction is becoming increasingly important as many companies employ recommender systems in their online businesses, e. g., personalized purchase prediction of shopping baskets.
One4all User Representation for Recommender Systems in E-commerce
General-purpose representation learning through large-scale pre-training has shown promising results in the various machine learning fields.
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance.
M2FN: Multi-step Modality Fusion for Advertisement Image Assessment
Assessing advertisements, specifically on the basis of user preferences and ad quality, is crucial to the marketing industry.
A Worrying Analysis of Probabilistic Time-series Models for Sales Forecasting
Probabilistic time-series models become popular in the forecasting field as they help to make optimal decisions under uncertainty.
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Our proposed method is learning to learn a primary task by predicting meta-paths as auxiliary tasks.
Multi-Manifold Learning for Large-scale Targeted Advertising System
The key to the success of precise user targeting lies in learning the accurate user and ad representation in the embedding space.
Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments
The hop sampling randomly selects the number of propagation steps rather than fixing it, and by doing so, it encourages the model to learn meaningful node representation for all intermediate propagation layers and to experience a variety of plausible graphs that are not in the training set.
Odds-Ratio Thompson Sampling to Control for Time-Varying Effect
Use of the proposed method in continuous experiment is described with discussing a desirable property of the method.
Which Ads to Show? Advertisement Image Assessment with Auxiliary Information via Multi-step Modality Fusion
Despite crucial influences of image quality, auxiliary information of ad images such as tags and target subjects can also determine image preference.
Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation
The oversmoothing of GNNs is an obstacle of GNN-based social recommendation as well.
Multimodal Dual Attention Memory for Video Story Question Answering
We confirm the best performance of the dual attention mechanism combined with late fusion by ablation studies.
Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks
A major obstacle in teaching machines to understand videos is the lack of training data, as creating temporal annotations for long videos requires a huge amount of human effort.
DeepStory: Video Story QA by Deep Embedded Memory Networks
This is mainly due to 1) the reconstruction of video stories in a scene-dialogue combined form that utilize the latent embedding and 2) attention.
