Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Finetuning Pretrained Transformers into RNNs
Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism’s complexity scales…
Sentence Bottleneck Autoencoders from Transformer Language Models
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders,…
Think about it! Improving defeasible reasoning by first modeling the question scenario
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning suggests that a…
Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization
Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to…
DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model…
Container: Context Aggregation Network
Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers – originally introduced in natural language…
SciA11y: Converting Scientific Papers to Accessible HTML
We present SciA11y, a system that renders inaccessible scientific paper PDFs into HTML. SciA11y uses machine learning models to extract and understand the content of scientific PDFs, and reorganizes…
Delphi: Towards Machine Ethics and Norms
Failing to account for moral norms could notably hinder AI systems’ ability to interact with people. AI systems empirically require social, cultural, and ethical norms to make moral judgments.…
Can Machines Learn Morality? The Delphi Experiment
As AI systems become increasingly powerful and pervasive, there are growing concerns about machines’ morality or a lack thereof. Yet, teaching morality to machines is a formidable task, as morality…
Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models
Publicly available, large pretrained Language Models (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to…