Alert button
Picture for Mark Dredze

Mark Dredze

Alert button

Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics

Nov 15, 2022
Carlos Aguirre, Mark Dredze, Philip Resnik

Figure 1 for Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics
Figure 2 for Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics
Figure 3 for Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics
Figure 4 for Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics
Viaarxiv icon

Zero-shot Cross-lingual Transfer is Under-specified Optimization

Jul 12, 2022
Shijie Wu, Benjamin Van Durme, Mark Dredze

Figure 1 for Zero-shot Cross-lingual Transfer is Under-specified Optimization
Figure 2 for Zero-shot Cross-lingual Transfer is Under-specified Optimization
Figure 3 for Zero-shot Cross-lingual Transfer is Under-specified Optimization
Figure 4 for Zero-shot Cross-lingual Transfer is Under-specified Optimization
Viaarxiv icon

The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic

Jun 22, 2022
Keith Harrigian, Mark Dredze

Figure 1 for The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic
Figure 2 for The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic
Figure 3 for The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic
Figure 4 for The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic
Viaarxiv icon

Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses

Jun 22, 2022
Keith Harrigian, Mark Dredze

Figure 1 for Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses
Figure 2 for Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses
Figure 3 for Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses
Figure 4 for Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses
Viaarxiv icon

What Makes Data-to-Text Generation Hard for Pretrained Language Models?

May 23, 2022
Moniba Keymanesh, Adrian Benton, Mark Dredze

Figure 1 for What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Figure 2 for What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Figure 3 for What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Figure 4 for What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Viaarxiv icon

Enriching Unsupervised User Embedding via Medical Concepts

Mar 29, 2022
Xiaolei Huang, Franck Dernoncourt, Mark Dredze

Figure 1 for Enriching Unsupervised User Embedding via Medical Concepts
Figure 2 for Enriching Unsupervised User Embedding via Medical Concepts
Figure 3 for Enriching Unsupervised User Embedding via Medical Concepts
Figure 4 for Enriching Unsupervised User Embedding via Medical Concepts
Viaarxiv icon

Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction

Sep 14, 2021
Mahsa Yarmohammadi, Shijie Wu, Marc Marone, Haoran Xu, Seth Ebner, Guanghui Qin, Yunmo Chen, Jialiang Guo, Craig Harman, Kenton Murray, Aaron Steven White, Mark Dredze, Benjamin Van Durme

Figure 1 for Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Figure 2 for Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Figure 3 for Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Figure 4 for Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Viaarxiv icon

Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information

Aug 01, 2021
Yuval Pinter, Amanda Stent, Mark Dredze, Jacob Eisenstein

Figure 1 for Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information
Figure 2 for Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information
Figure 3 for Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information
Figure 4 for Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information
Viaarxiv icon

Improving Zero-Shot Multi-Lingual Entity Linking

Apr 16, 2021
Elliot Schumacher, James Mayfield, Mark Dredze

Figure 1 for Improving Zero-Shot Multi-Lingual Entity Linking
Figure 2 for Improving Zero-Shot Multi-Lingual Entity Linking
Figure 3 for Improving Zero-Shot Multi-Lingual Entity Linking
Figure 4 for Improving Zero-Shot Multi-Lingual Entity Linking
Viaarxiv icon

Faithful and Plausible Explanations of Medical Code Predictions

Apr 16, 2021
Zach Wood-Doughty, Isabel Cachola, Mark Dredze

Figure 1 for Faithful and Plausible Explanations of Medical Code Predictions
Figure 2 for Faithful and Plausible Explanations of Medical Code Predictions
Figure 3 for Faithful and Plausible Explanations of Medical Code Predictions
Figure 4 for Faithful and Plausible Explanations of Medical Code Predictions
Viaarxiv icon