Search Results for author: SHimei Pan

Found 21 papers, 2 papers with code

Incorporating medical knowledge in BERT for clinical relation extraction

no code implementations EMNLP 2021 Arpita Roy, SHimei Pan

In recent years pre-trained language models (PLM) such as BERT have proven to be very effective in diverse NLP tasks such as Information Extraction, Sentiment Analysis and Question Answering.

Question Answering Relation Extraction +1

User Acceptance of Gender Stereotypes in Automated Career Recommendations

no code implementations13 Jun 2021 Clarice Wang, Kathryn Wang, Andrew Bian, Rashidul Islam, Kamrun Naher Keya, James Foulds, SHimei Pan

In other words, our results demonstrate we cannot fully address the gender bias issue in AI recommendations without addressing the gender bias in humans.

Learning User Embeddings from Temporal Social Media Data: A Survey

no code implementations17 May 2021 Fatema Hasan, Kevin S. Xu, James R. Foulds, SHimei Pan

User-generated data on social media contain rich information about who we are, what we like and how we make decisions.

Representation Learning

Analyzing COVID-19 Tweets with Transformer-based Language Models

no code implementations20 Apr 2021 Philip Feldman, Sim Tiwari, Charissa S. L. Cheah, James R. Foulds, SHimei Pan

This paper describes a method for using Transformer-based Language Models (TLMs) to understand public opinion from social media posts.

Fair Representation Learning for Heterogeneous Information Networks

1 code implementation18 Apr 2021 Ziqian Zeng, Rashidul Islam, Kamrun Naher Keya, James Foulds, Yangqiu Song, SHimei Pan

Recently, much attention has been paid to the societal impact of AI, especially concerns regarding its fairness.

Fairness Representation Learning

Equitable Allocation of Healthcare Resources with Fair Cox Models

no code implementations14 Oct 2020 Kamrun Naher Keya, Rashidul Islam, SHimei Pan, Ian Stockwell, James R. Foulds

Healthcare programs such as Medicaid provide crucial services to vulnerable populations, but due to limited resources, many of the individuals who need these services the most languish on waiting lists.

Fairness

Causal Feature Selection with Dimension Reduction for Interpretable Text Classification

no code implementations9 Oct 2020 Guohou Shan, James Foulds, SHimei Pan

Text features that are correlated with class labels, but do not directly cause them, are sometimesuseful for prediction, but they may not be insightful.

Causal Inference Classification +4

Neural Fair Collaborative Filtering

no code implementations2 Sep 2020 Rashidul Islam, Kamrun Naher Keya, Ziqian Zeng, SHimei Pan, James Foulds

A growing proportion of human interactions are digitized on social media platforms and subjected to algorithmic decision-making, and it has become increasingly important to ensure fair treatment from these algorithms.

Collaborative Filtering Decision Making +2

Supervising Unsupervised Open Information Extraction Models

no code implementations IJCNLP 2019 Arpita Roy, Youngja Park, Taesung Lee, SHimei Pan

We propose a novel supervised open information extraction (Open IE) framework that leverages an ensemble of unsupervised Open IE systems and a small amount of labeled data to improve system performance.

Open Information Extraction Role Embedding

Predicting Malware Attributes from Cybersecurity Texts

no code implementations NAACL 2019 Arpita Roy, Youngja Park, SHimei Pan

Text analytics is a useful tool for studying malware behavior and tracking emerging threats.

Bayesian Modeling of Intersectional Fairness: The Variance of Bias

no code implementations18 Nov 2018 James Foulds, Rashidul Islam, Kamrun Keya, SHimei Pan

Intersectionality is a framework that analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability.

Fairness

An Intersectional Definition of Fairness

1 code implementation22 Jul 2018 James Foulds, Rashidul Islam, Kamrun Naher Keya, SHimei Pan

We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens arising from the Humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability.

Fairness

UMBC at SemEval-2018 Task 8: Understanding Text about Malware

no code implementations SEMEVAL 2018 Ankur Padia, Arpita Roy, Taneeya Satyapanich, Francis Ferraro, SHimei Pan, Youngja Park, Anupam Joshi, Tim Finin

We describe the systems developed by the UMBC team for 2018 SemEval Task 8, SecureNLP (Semantic Extraction from CybersecUrity REports using Natural Language Processing).

Automatically Infer Human Traits and Behavior from Social Media Data

no code implementations11 Apr 2018 Shimei Pan, Tao Ding

Given the complexity of human minds and their behavioral flexibility, it requires sophisticated data analysis to sift through a large amount of human behavioral evidence to model human minds and to predict human behavior.

Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction

no code implementations EMNLP 2017 Tao Ding, Warren K. Bickel, SHimei Pan

In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems.

Social Media-based Substance Use Prediction

no code implementations16 May 2017 Tao Ding, Warren K. Bickel, SHimei Pan

In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems.

\$1 Today or \$2 Tomorrow? The Answer is in Your Facebook Likes

no code implementations22 Mar 2017 Tao Ding, Warren K. Bickel, SHimei Pan

In economics and psychology, delay discounting is often used to characterize how individuals choose between a smaller immediate reward and a larger delayed reward.

Decision Making

Personalized Emphasis Framing for Persuasive Message Generation

no code implementations EMNLP 2016 Tao Ding, SHimei Pan

In this paper, we present a study on personalized emphasis framing which can be used to tailor the content of a message to enhance its appeal to different individuals.

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