Search Results for author:
Found 11 papers, 5 papers with code
Sequence-to-Lattice Models for Fast Translation
Non-autoregressive machine translation (NAT) approaches enable fast generation by utilizing parallelizable generative processes.
Torch-Struct: Deep Structured Prediction Library
The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks.
Simple Guidance Mechanisms for Discrete Diffusion Models
Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms.
Simple and Effective Masked Diffusion Language Models
While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling.
Ranked #1 on
Language Modelling
on One Billion Word
Developmental Stage Classification of EmbryosUsing Two-Stream Neural Network with Linear-Chain Conditional Random Field
In this work, we propose a two-stream model for developmental stage classification.
Template Filling with Generative Transformers
Template filling is generally tackled by a pipeline of two separate supervised systems {--} one for role-filler extraction and another for template/event recognition.
Improving Event Duration Prediction via Time-aware Pre-training
End-to-end models in NLP rarely encode external world knowledge about length of time.
Transformers: State-of-the-Art Natural Language Processing
Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks.
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.
Tensor Variable Elimination for Plated Factor Graphs
To exploit efficient tensor algebra in graphs with plates of variables, we generalize undirected factor graphs to plated factor graphs and variable elimination to a tensor variable elimination algorithm that operates directly on plated factor graphs.
On the Flip Side: Identifying Counterexamples in Visual Question Answering
Visual question answering (VQA) models respond to open-ended natural language questions about images.
