• Publications
  • Influence
Knowledge Enhanced Contextual Word Representations
After integrating WordNet and a subset of Wikipedia into BERT, the knowledge enhanced BERT (KnowBert) demonstrates improved perplexity, ability to recall facts as measured in a probing task and downstream performance on relationship extraction, entity typing, and word sense disambiguation. Expand
Eliciting Knowledge from Language Models Using Automatically Generated Prompts
The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problemsExpand
COVIDLies: Detecting COVID-19 Misinformation on Social Media
COVIDLIES1, a dataset of 6761 expert-annotated tweets to evaluate the performance of misinformation detection systems on 86 different pieces of COVID-19 related misinformation, is released, providing initial benchmarks and identifying key challenges for future models to improve upon. Expand
Barack’s Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling
This work introduces the knowledge graph language model (KGLM), a neural language model with mechanisms for selecting and copying facts from a knowledge graph that are relevant to the context that enable the model to render information it has never seen before, as well as generate out-of-vocabulary tokens. Expand
Detecting conversation topics in primary care office visits from transcripts of patient-provider interactions
Investigating the effectiveness of machine learning methods for automated annotation of medical topics in patient-provider dialog transcripts finds that incorporating sequential information across talk-turns improves the accuracy of topic prediction in patients' dialog by smoothing out noisy information from talk- turns. Expand
Active Bayesian Assessment for Black-Box Classifiers
This paper develops inference strategies to quantify uncertainty for common assessment metrics (accuracy, misclassification cost, expected calibration error), and proposes a framework for active assessment using this uncertainty to guide efficient selection of instances for labeling. Expand
Detecting COVID-19 Misinformation on Social Media
The ongoing pandemic has heightened the need for developing tools to flag COVID-19related misinformation on the internet, specifically on social media such as Twitter. However, due to novel languageExpand
Multimodal Attribute Extraction
A dataset containing mixed-media data for over 2 million product items along with 7 million attribute-value pairs describing the items can be used to train attribute extractors in a weakly supervised manner and a variety of baselines are provided which demonstrate the relative effectiveness of the individual modes of information towards solving the task. Expand
Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models
This work shows that finetuning LMs in the few- shot setting can considerably reduce the need for prompt engineering, and recommends finetuned LMs for few-shot learning as it is more accurate, robust to different prompts, and can be made nearly as efficient as using frozen LMs. Expand
PoMo: Generating Entity-Specific Post-Modifiers in Context
PoMo, a post-modifier dataset created automatically from news articles reflecting a journalistic need for incorporating entity information that is relevant to a particular news event, is built. Expand