research
∙
05/26/2023
MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
Autoregressive language models are trained by minimizing the cross-entro...
share
research
∙
05/22/2023
Generalizing Fairness using Multi-Task Learning without Demographic Information
To ensure the fairness of machine learning systems, we can include a fai...
research
∙
03/30/2023
BloombergGPT: A Large Language Model for Finance
The use of NLP in the realm of financial technology is broad and complex...
research
∙
12/13/2022
Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?
Traditional multi-task learning architectures train a single model acros...
research
∙
11/15/2022
Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics
Stressors are related to depression, but this relationship is complex. W...
research
∙
07/12/2022
Zero-shot Cross-lingual Transfer is Under-specified Optimization
Pretrained multilingual encoders enable zero-shot cross-lingual transfer...
research
∙
06/22/2022
The Problem of Semantic Shift in Longitudinal Monitoring of Social Media: A Case Study on Mental Health During the COVID-19 Pandemic
Social media allows researchers to track societal and cultural changes o...
research
∙
06/22/2022
Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses
Self-disclosed mental health diagnoses, which serve as ground truth anno...
research
∙
05/23/2022
What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Expressing natural language descriptions of structured facts or relation...
research
∙
03/20/2022
Enriching Unsupervised User Embedding via Medical Concepts
Clinical notes in Electronic Health Records (EHR) present rich documente...
research
∙
09/14/2021
Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Zero-shot cross-lingual information extraction (IE) describes the constr...
research
∙
08/01/2021
Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information
Commonly-used transformer language models depend on a tokenization schem...
research
∙
04/16/2021
Improving Zero-Shot Multi-Lingual Entity Linking
Entity linking – the task of identifying references in free text to rele...
research
∙
04/16/2021
Faithful and Plausible Explanations of Medical Code Predictions
Machine learning models that offer excellent predictive performance ofte...
research
∙
04/11/2021
Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling
Neural topic models can augment or replace bag-of-words inputs with the ...
research
∙
03/18/2021
Gender and Racial Fairness in Depression Research using Social Media
Multiple studies have demonstrated that behavior on internet-based socia...
research
∙
02/22/2021
User Factor Adaptation for User Embedding via Multitask Learning
Language varies across users and their interested fields in social media...
research
∙
02/10/2021
Generating Synthetic Text Data to Evaluate Causal Inference Methods
Drawing causal conclusions from observational data requires making assum...
research
∙
11/16/2020
Examining the Feasibility of Off-the-Shelf Algorithms for Masking Directly Identifiable Information in Social Media Data
The identification and removal/replacement of protected information from...
research
∙
11/10/2020
On the State of Social Media Data for Mental Health Research
Data-driven methods for mental health treatment and surveillance have be...
research
∙
10/19/2020
Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking
Cross-language entity linking grounds mentions in multiple languages to ...
research
∙
10/13/2020
Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement
The #MeToo movement on Twitter has drawn attention to the pervasive natu...
research
∙
10/06/2020
Do Explicit Alignments Robustly Improve Multilingual Encoders?
Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised mul...
research
∙
05/18/2020
Are All Languages Created Equal in Multilingual BERT?
Multilingual BERT (mBERT) trained on 104 languages has shown surprisingl...
research
∙
05/02/2020
Sources of Transfer in Multilingual Named Entity Recognition
Named-entities are inherently multilingual, and annotations in any given...
research
∙
05/01/2020
Using Noisy Self-Reports to Predict Twitter User Demographics
Computational social science studies often contextualize content analysi...
research
∙
10/30/2019
Phenotyping of Clinical Notes with Improved Document Classification Models Using Contextualized Neural Language Models
Clinical notes contain an extensive record of a patient's health status,...
research
∙
04/19/2019
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
Pretrained contextual representation models (Peters et al., 2018; Devlin...
research
∙
10/01/2018
Challenges of Using Text Classifiers for Causal Inference
Causal understanding is essential for many kinds of decision-making, but...
research
∙
09/11/2018
Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning
Technical and fundamental analysis are traditional tools used to analyze...
research
∙
02/22/2017
Feature Generation for Robust Semantic Role Labeling
Hand-engineered feature sets are a well understood method for creating r...
research
∙
02/19/2017
Harmonic Grammar, Optimality Theory, and Syntax Learnability: An Empirical Exploration of Czech Word Order
This work presents a systematic theoretical and empirical comparison of ...
research
∙
08/09/2016
Multi-task Domain Adaptation for Sequence Tagging
Many domain adaptation approaches rely on learning cross domain shared r...
research
∙
06/20/2016
Twitter as a Source of Global Mobility Patterns for Social Good
Data on human spatial distribution and movement is essential for underst...
research
∙
04/02/2016
Embedding Lexical Features via Low-Rank Tensors
Modern NLP models rely heavily on engineered features, which often combi...
research
∙
03/02/2016
Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
Named entity recognition, and other information extraction tasks, freque...
research
∙
08/10/2015
Approximation-Aware Dependency Parsing by Belief Propagation
We show how to train the fast dependency parser of Smith and Eisner (200...
research
∙
05/31/2015
Interactive Knowledge Base Population
Most work on building knowledge bases has focused on collecting entities...
research
∙
05/10/2015