Search Results for author:
Found 31 papers, 15 papers with code
Sequence-to-Lattice Models for Fast Translation
Non-autoregressive machine translation (NAT) approaches enable fast generation by utilizing parallelizable generative processes.
Implicit Chain of Thought Reasoning via Knowledge Distillation
In this work, we explore an alternative reasoning approach: instead of explicitly producing the chain of thought reasoning steps, we use the language model's internal hidden states to perform implicit reasoning.
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
Prompting language models (LMs) is the main interface for applying them to new tasks.
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences.
Model Criticism for Long-Form Text Generation
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 progression).
Markup-to-Image Diffusion Models with Scheduled Sampling
These experiments each verify the effectiveness of the diffusion process and the use of scheduled sampling to fix generation issues.
Semi-Parametric Inducing Point Networks and Neural Processes
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.
Low-Rank Constraints for Fast Inference in Structured Models
This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models.
Rationales for Sequential Predictions
Compared to existing baselines, greedy rationalization is best at optimizing the combinatorial objective and provides the most faithful rationales.
Weighted Gaussian Process Bandits for Non-stationary Environments
To this end, we develop WGP-UCB, a novel UCB-type algorithm based on weighted Gaussian process regression.
Incentive Design and Profit Sharing in Multi-modal Transportation Network
Accordingly, in this paper, we use cooperative game theory coupled with the hyperpath-based stochastic user equilibrium framework to study such a market.
Cascaded Text Generation with Markov Transformers
The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies.
Residual Energy-Based Models for Text Generation
In this work, we investigate un-normalized energy-based models (EBMs) which operate not at the token but at the sequence level.
Residual Energy-Based Models for Text
Current large-scale auto-regressive language models display impressive fluency and can generate convincing text.
AdaptivFloat: A Floating-point based Data Type for Resilient Deep Learning Inference
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 adequately capture the wide data distributions commonly seen in sequence transduction models.
Neural Linguistic Steganography
Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal.
Real or Fake? Learning to Discriminate Machine from Human Generated Text
Energy-based models (EBMs), a. k. a.
Bottom-Up Abstractive Summarization
We use this selector as a bottom-up attention step to constrain the model to likely phrases.
Ranked #4 on
Multi-Document Summarization
on Multi-News
Latent Alignment and Variational Attention
This work considers variational attention networks, alternatives to soft and hard attention for learning latent variable alignment models, with tighter approximation bounds based on amortized variational inference.
Ranked #28 on
Machine Translation
on IWSLT2014 German-English
OpenNMT: Neural Machine Translation Toolkit
OpenNMT is an open-source toolkit for neural machine translation (NMT).
OpenNMT: Open-source Toolkit for Neural Machine Translation
We introduce an open-source toolkit for neural machine translation (NMT) to support research into model architectures, feature representations, and source modalities, while maintaining competitive performance, modularity and reasonable training requirements.
Learning Latent Space Models with Angular Constraints
The large model capacity of latent space models (LSMs) enables them to achieve great performance on various applications, but meanwhile renders LSMs to be prone to overfitting.
OpenNMT: Open-Source Toolkit for Neural Machine Translation
We describe an open-source toolkit for neural machine translation (NMT).
Dropout with Expectation-linear Regularization
Algorithmically, we show that our proposed measure of the inference gap can be used to regularize the standard dropout training objective, resulting in an \emph{explicit} control of the gap.
Image-to-Markup Generation with Coarse-to-Fine Attention
We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism.
Neural Machine Translation with Recurrent Attention Modeling
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 future.
Learning Concept Taxonomies from Multi-modal Data
We study the problem of automatically building hypernym taxonomies from textual and visual data.
Latent Variable Modeling with Diversity-Inducing Mutual Angular Regularization
On two popular latent variable models --- restricted Boltzmann machine and distance metric learning, we demonstrate that MAR can effectively capture long-tail patterns, reduce model complexity without sacrificing expressivity and improve interpretability.
On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
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 issues involved in latent variable modeling: (1) how to capture long-tail patterns underlying data; (2) how to reduce model complexity without sacrificing expressivity; (3) how to improve the interpretability of learned patterns.
Creating Scalable and Interactive Web Applications Using High Performance Latent Variable Models
In this project we outline a modularized, scalable system for comparing Amazon products in an interactive and informative way using efficient latent variable models and dynamic visualization.
