87 citations · 454 across the 22 of their papers we have counts for
25 papers
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
John X. Morris, Chandan Singh, Alexander M. Rush +2
Prompting language models (LMs) is the main interface for applying them to new tasks. However, for smaller LMs, prompting provides low accuracy compared to gradient-based finetunin…
Model Criticism for Long-Form Text Generation
Yuntian Deng, Volodymyr Kuleshov, Alexander M. Rush
Language models have demonstrated the ability to generate highly fluent text; however, it remains unclear whether their output retains coherent high-level structure (e.g., story pr…
Markup-to-Image Diffusion Models with Scheduled Sampling
Yuntian Deng, Noriyuki Kojima, Alexander M. Rush
Building on recent advances in image generation, we present a fully data-driven approach to rendering markup into images. The approach is based on diffusion models, which parameter…
Semi-Parametric Inducing Point Networks and Neural Processes
Richa Rastogi, Yair Schiff, Alon Hacohen +5
We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner. Semi-pa…
Low-Rank Constraints for Fast Inference in Structured Models
Justin T. Chiu, Yuntian Deng, Alexander M. Rush
Structured distributions, i.e. distributions over combinatorial spaces, are commonly used to learn latent probabilistic representations from observed data. However, scaling these m…
Rationales for Sequential Predictions
Keyon Vafa, Yuntian Deng, David M. Blei +1
Sequence models are a critical component of modern NLP systems, but their predictions are difficult to explain. We consider model explanations though rationales, subsets of context…
Cascaded Text Generation with Markov Transformers
Yuntian Deng, Alexander M. Rush
The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding wit…
Residual Energy-Based Models for Text Generation
Yuntian Deng, Anton Bakhtin, Myle Ott +2
Text generation is ubiquitous in many NLP tasks, from summarization, to dialogue and machine translation. The dominant parametric approach is based on locally normalized models whi…
Residual Energy-Based Models for Text
Anton Bakhtin, Yuntian Deng, Sam Gross +3
Current large-scale auto-regressive language models display impressive fluency and can generate convincing text. In this work we start by asking the question: Can the generations o…
Neural Linguistic Steganography
Zachary M. Ziegler, Yuntian Deng, Alexander M. Rush
Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into…
AdaptivFloat: A Floating-point based Data Type for Resilient Deep Learning Inference
Thierry Tambe, En-Yu Yang, Zishen Wan +5
Conventional hardware-friendly quantization methods, such as fixed-point or integer, tend to perform poorly at very low word sizes as their shrinking dynamic ranges cannot adequate…
Real or Fake? Learning to Discriminate Machine from Human Generated Text
Anton Bakhtin, Sam Gross, Myle Ott +3
Energy-based models (EBMs), a.k.a. un-normalized models, have had recent successes in continuous spaces. However, they have not been successfully applied to model text sequences. W…
Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning
Ran Zhao, Yuntian Deng, Mark Dredze +3
Technical and fundamental analysis are traditional tools used to analyze individual stocks; however, the finance literature has shown that the price movement of each individual sto…
Bottom-Up Abstractive Summarization
Sebastian Gehrmann, Yuntian Deng, Alexander M. Rush
Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work propose…
Latent Alignment and Variational Attention
Yuntian Deng, Yoon Kim, Justin Chiu +2
Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method…
OpenNMT: Neural Machine Translation Toolkit
Guillaume Klein, Yoon Kim, Yuntian Deng +3
OpenNMT is an open-source toolkit for neural machine translation (NMT). The system prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research in…
OpenNMT: Open-source Toolkit for Neural Machine Translation
Guillaume Klein, Yoon Kim, Yuntian Deng +3
We introduce an open-source toolkit for neural machine translation (NMT) to support research into model architectures, feature representations, and source modalities, while maintai…
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Guillaume Klein, Yoon Kim, Yuntian Deng +2
We describe an open-source toolkit for neural machine translation (NMT). The toolkit prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research…
Dropout with Expectation-linear Regularization
Xuezhe Ma, Yingkai Gao, Zhiting Hu +3
Dropout, a simple and effective way to train deep neural networks, has led to a number of impressive empirical successes and spawned many recent theoretical investigations. However…
Image-to-Markup Generation with Coarse-to-Fine Attention
Yuntian Deng, Anssi Kanervisto, Jeffrey Ling +1
We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism. Our method is evaluated in the contex…
Neural Machine Translation with Recurrent Attention Modeling
Zichao Yang, Zhiting Hu, Yuntian Deng +2
Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the…
Learning Concept Taxonomies from Multi-modal Data
Hao Zhang, Zhiting Hu, Yuntian Deng +3
We study the problem of automatically building hypernym taxonomies from textual and visual data. Previous works in taxonomy induction generally ignore the increasingly prominent vi…
Latent Variable Modeling with Diversity-Inducing Mutual Angular Regularization
Pengtao Xie, Yuntian Deng, Eric Xing
Latent Variable Models (LVMs) are a large family of machine learning models providing a principled and effective way to extract underlying patterns, structure and knowledge from ob…
On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
Pengtao Xie, Yuntian Deng, Eric Xing
Recently diversity-inducing regularization methods for latent variable models (LVMs), which encourage the components in LVMs to be diverse, have been studied to address several iss…