Search Results for author: Ee-Peng Lim

Found 37 papers, 22 papers with code

Guided Attention Multimodal Multitask Financial Forecasting with Inter-Company Relationships and Global and Local News

no code implementations ACL 2022 Gary Ang, Ee-Peng Lim

Most works on financial forecasting use information directly associated with individual companies (e. g., stock prices, news on the company) to predict stock returns for trading.

Management

Speaker Verification in Agent-Generated Conversations

no code implementations16 May 2024 Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim

The recent success of large language models (LLMs) has attracted widespread interest to develop role-playing conversational agents personalized to the characteristics and styles of different speakers to enhance their abilities to perform both general and special purpose dialogue tasks.

Speaker Verification

OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation

no code implementations CVPR 2024 Xiongwei Wu, Sicheng Yu, Ee-Peng Lim, Chong-Wah Ngo

The pre-training phase equips FoodLearner with the capability to align visual information with corresponding textual representations that are specifically related to food, while the second phase adapts both the FoodLearner and the Image-Informed Text Encoder for the segmentation task.

Image Segmentation Segmentation +1

All in an Aggregated Image for In-Image Learning

1 code implementation28 Feb 2024 Lei Wang, Wanyu Xu, Zhiqiang Hu, Yihuai Lan, Shan Dong, Hao Wang, Roy Ka-Wei Lee, Ee-Peng Lim

This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (I$^2$L) that combines demonstration examples, visual cues, and chain-of-thought reasoning into an aggregated image to enhance the capabilities of Large Multimodal Models (e. g., GPT-4V) in multimodal reasoning tasks.

Hallucination In-Context Learning +1

Generative Semi-supervised Graph Anomaly Detection

1 code implementation19 Feb 2024 Hezhe Qiao, Qingsong Wen, XiaoLi Li, Ee-Peng Lim, Guansong Pang

This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the extensively explored unsupervised setting with a fully unlabeled graph.

Graph Anomaly Detection One-class classifier

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites

1 code implementation4 Dec 2023 Lei Wang, Jiabang He, Shenshen Li, Ning Liu, Ee-Peng Lim

The fine-grained object attributes and behaviors non-existent in the image may still be generated but not measured by the current evaluation methods.

Hallucination Hallucination Evaluation +2

On Exploring the Reasoning Capability of Large Language Models with Knowledge Graphs

no code implementations1 Dec 2023 Pei-Chi Lo, Yi-Hang Tsai, Ee-Peng Lim, San-Yih Hwang

Two research questions are formulated to investigate the accuracy of LLMs in recalling information from pre-training knowledge graphs and their ability to infer knowledge graph relations from context.

Hallucination Knowledge Graphs

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

1 code implementation23 Oct 2023 Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang

To achieve this goal, we adopt Avalon, a representative communication game, as the environment and use system prompts to guide LLM agents to play the game.

LLM4Vis: Explainable Visualization Recommendation using ChatGPT

1 code implementation11 Oct 2023 Lei Wang, Songheng Zhang, Yun Wang, Ee-Peng Lim, Yong Wang

To obtain demonstration examples with high-quality explanations, we propose a new explanation generation bootstrapping to iteratively refine generated explanations by considering the previous generation and template-based hint.

Data Visualization Explanation Generation

Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

3 code implementations6 May 2023 Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, Ee-Peng Lim

To address the calculation errors and improve the quality of generated reasoning steps, we extend PS prompting with more detailed instructions and derive PS+ prompting.

Math

Zero-Shot Next-Item Recommendation using Large Pretrained Language Models

1 code implementation6 Apr 2023 Lei Wang, Ee-Peng Lim

Large language models (LLMs) have achieved impressive zero-shot performance in various natural language processing (NLP) tasks, demonstrating their capabilities for inference without training examples.

Sequential Recommendation

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

2 code implementations4 Apr 2023 Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e. g., ChatDoctor) or instruction data (e. g., Alpaca).

Arithmetic Reasoning Language Modelling

Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames

1 code implementation16 Oct 2022 Ning Han, Xun Yang, Ee-Peng Lim, Hao Chen, Qianru Sun

In turn, the frame-level optimization is through gradient descent using the meta loss of video retrieval model computed on the whole video.

Bilevel Optimization Retrieval +2

Explanation Guided Contrastive Learning for Sequential Recommendation

1 code implementation3 Sep 2022 Lei Wang, Ee-Peng Lim, Zhiwei Liu, Tianxiang Zhao

Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions.

Contrastive Learning Representation Learning +1

Improving Compositional Generalization in Math Word Problem Solving

1 code implementation3 Sep 2022 Yunshi Lan, Lei Wang, Jing Jiang, Ee-Peng Lim

To improve the compositional generalization in MWP solving, we propose an iterative data augmentation method that includes diverse compositional variation into training data and could collaborate with MWP methods.

Data Augmentation Math +1

Attention-based Feature Aggregation

no code implementations29 Sep 2021 Xiongwei Wu, Ee-Peng Lim, Steven Hoi, Qianru Sun

To implement this module, we define two variants of attention: self-attention on the summed-up feature map, and cross-attention between two feature maps before summed up.

Instance Segmentation object-detection +2

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset

1 code implementation Findings (EMNLP) 2021 Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.

Graph Question Answering Question Answering

A Large-Scale Benchmark for Food Image Segmentation

2 code implementations12 May 2021 Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C. H. Hoi, Qianru Sun

Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks -- the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e. g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different food images.

Ranked #3 on Semantic Segmentation on FoodSeg103 (using extra training data)

Image Segmentation Segmentation +1

ENCONTER: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer

1 code implementation EACL 2021 Lee-Hsun Hsieh, Yang-Yin Lee, Ee-Peng Lim

Pretrained using large amount of data, autoregressive language models are able to generate high quality sequences.

Text Generation

DeepStyle: User Style Embedding for Authorship Attribution of Short Texts

no code implementations14 Mar 2021 Zhiqiang Hu, Roy Ka-Wei Lee, Lei Wang, Ee-Peng Lim, Bo Dai

Authorship attribution (AA), which is the task of finding the owner of a given text, is an important and widely studied research topic with many applications.

Authorship Attribution text-classification +1

Transforming Facial Weight of Real Images by Editing Latent Space of StyleGAN

1 code implementation5 Nov 2020 V N S Rama Krishna Pinnimty, Matt Zhao, Palakorn Achananuparp, Ee-Peng Lim

We present an invert-and-edit framework to automatically transform facial weight of an input face image to look thinner or heavier by leveraging semantic facial attributes encoded in the latent space of Generative Adversarial Networks (GANs).

Attribute

On Predicting Personal Values of Social Media Users using Community-Specific Language Features and Personal Value Correlation

no code implementations16 Jul 2020 Amila Silva, Pei-Chi Lo, Ee-Peng Lim

Moreover, we use the stack model to predict the personal values of a large community of Twitter users using their public tweet content and empirically derive several interesting findings about their online behavior consistent with earlier findings in the social science and social media literature.

Decision Making

Face to Purchase: Predicting Consumer Choices with Structured Facial and Behavioral Traits Embedding

no code implementations14 Jul 2020 Zhe Liu, Xianzhi Wang, Lina Yao, Jake An, Lei Bai, Ee-Peng Lim

We design a semi-supervised model based on a hierarchical embedding network to extract high-level features of consumers and to predict the top-$N$ purchase destinations of a consumer.

Graph-to-Tree Learning for Solving Math Word Problems

1 code implementation ACL 2020 Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim

While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well.

Decoder Math +1

Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism

no code implementations9 Mar 2020 Hao Wang, Doyen Sahoo, Chenghao Liu, Ke Shu, Palakorn Achananuparp, Ee-Peng Lim, Steven C. H. Hoi

Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc.

Cross-Modal Retrieval Retrieval

RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System

1 code implementation5 Mar 2020 Helena H. Lee, Ke Shu, Palakorn Achananuparp, Philips Kokoh Prasetyo, Yue Liu, Ee-Peng Lim, Lav R. Varshney

Interests in the automatic generation of cooking recipes have been growing steadily over the past few years thanks to a large amount of online cooking recipes.

Language Modelling Recipe Generation +1

JPLink: On Linking Jobs to Vocational Interest Types

no code implementations6 Feb 2020 Amila Silva, Pei-Chi Lo, Ee-Peng Lim

To cope with assigning massive number of jobs with RIASEC labels, we propose JPLink, a machine learning approach using the text content in job titles and job descriptions.

Learning-To-Rank

Estimating Glycemic Impact of Cooking Recipes via Online Crowdsourcing and Machine Learning

1 code implementation17 Sep 2019 Helena Lee, Palakorn Achananuparp, Yue Liu, Ee-Peng Lim, Lav R. Varshney

Consumption of diets with low glycemic impact is highly recommended for diabetics and pre-diabetics as it helps maintain their blood glucose levels.

BIG-bench Machine Learning

A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits

no code implementations27 Aug 2019 Huozhi Zhou, Lingda Wang, Lav R. Varshney, Ee-Peng Lim

Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at unknown time steps.

Change Detection Multi-Armed Bandits

Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images

2 code implementations CVPR 2019 Hao Wang, Doyen Sahoo, Chenghao Liu, Ee-Peng Lim, Steven C. H. Hoi

Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle.

Cross-Modal Retrieval Nutrition +2

JobComposer: Career Path Optimization via Multicriteria Utility Learning

no code implementations4 Sep 2018 Richard J. Oentaryo, Xavier Jayaraj Siddarth Ashok, Ee-Peng Lim, Philips Kokoh Prasetyo

Its key premise is that the observed career trajectories in OPNs may not necessarily be optimal, and can be improved by learning to maximize the sum of payoffs attainable by following a career path.

Collective Semi-Supervised Learning for User Profiling in Social Media

no code implementations24 Jun 2016 Richard J. Oentaryo, Ee-Peng Lim, Freddy Chong Tat Chua, Jia-Wei Low, David Lo

The abundance of user-generated data in social media has incentivized the development of methods to infer the latent attributes of users, which are crucially useful for personalization, advertising and recommendation.

Cannot find the paper you are looking for? You can Submit a new open access paper.