• Publications
  • Influence
The Risk of Racial Bias in Hate Speech Detection
TLDR
This work proposes *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive.
Social Bias Frames: Reasoning about Social and Power Implications of Language
TLDR
It is found that while state-of-the-art neural models are effective at high-level categorization of whether a given statement projects unwanted social bias, they are not effective at spelling out more detailed explanations in terms of Social Bias Frames.
MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
TLDR
A large-scale dataset of math word problems and an interpretable neural math problem solver by learning to map problems to their operation programs and a new representation language to model operation programs corresponding to each math problem that aim to improve both the performance and the interpretability of the learned models.
Paragraph-Level Commonsense Transformers with Recurrent Memory
TLDR
PARA-COMeT, a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives, outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.
GO FIGURE: A Meta Evaluation of Factuality in Summarization
TLDR
This paper introduces a meta-evaluation framework for evaluating factual consistency metrics and experiments with nine recent factuality metrics using synthetic and human-labeled factuality data from short news, long news and dialogue summarization domains.
Cooperative Generator-Discriminator Networks for Abstractive Summarization with Narrative Flow
TLDR
To promote research toward abstractive summarization with narrative flow, a new dataset is introduced, Scientific Abstract SummarieS (SASS), where the abstracts are used as proxy gold summaries for scientific articles and Co-opNet is proposed, a novel transformer-based framework where the generator works with the discourse discriminator to compose a long-form summary.
EARLY FUSION for Goal Directed Robotic Vision
TLDR
This work introduces EARLYFUSION vision models that condition on a goal to build custom representations for downstream tasks, and shows that these goal specific representations can be learned more quickly, are substantially more parameter efficient, and more robust than existing attention mechanisms in the domain.
Discourse Understanding and Factual Consistency in Abstractive Summarization
TLDR
A general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary is introduced and empirical results demonstrate that Co-opNet learns to summarize with considerably improved global coherence compared to competitive baselines.
Detecting and Tracking Communal Bird Roosts in Weather Radar Data
TLDR
A machine learning system to detect and track roost signatures in weather radar data that detects previously unknown roosting locations and provides comprehensive spatio-temporal data about roosts across the US.
Modeling Swallow Roosts Using Weather Radar
...
1
2
...