research
∙
06/21/2023
OBELISC: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
Large multimodal models trained on natural documents, which interleave i...
share
research
∙
05/25/2023
Scaling Data-Constrained Language Models
The current trend of scaling language models involves increasing both pa...
research
∙
05/24/2023
Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations
Abductive reasoning aims to find plausible explanations for an event. Th...
research
∙
05/23/2023
HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision
Explainable multi-hop question answering (QA) not only predicts answers ...
research
∙
12/20/2022
Pretraining Without Attention
Transformers have been essential to pretraining success in NLP. Other ar...
research
∙
10/25/2022
Teal: Learning-Accelerated Optimization of Traffic Engineering
In the last decade, global cloud wide-area networks (WANs) have grown 10...
research
∙
10/24/2022
ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition
Speech recognition applications cover a range of different audio and tex...
research
∙
10/20/2022
Unsupervised Text Deidentification
Deidentification seeks to anonymize textual data prior to distribution. ...
research
∙
10/16/2022
Model Criticism for Long-Form Text Generation
Language models have demonstrated the ability to generate highly fluent ...
research
∙
10/11/2022
Markup-to-Image Diffusion Models with Scheduled Sampling
Building on recent advances in image generation, we present a fully data...
research
∙
08/16/2022
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models
State-of-the-art neural language models can now be used to solve ad-hoc ...
research
∙
02/02/2022
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
PromptSource is a system for creating, sharing, and using natural langua...
research
∙
01/08/2022
Low-Rank Constraints for Fast Inference in Structured Models
Structured distributions, i.e. distributions over combinatorial spaces, ...
research
∙
10/19/2021
GenNI: Human-AI Collaboration for Data-Backed Text Generation
Table2Text systems generate textual output based on structured data util...
research
∙
10/15/2021
Multitask Prompted Training Enables Zero-Shot Task Generalization
Large language models have recently been shown to attain reasonable zero...
research
∙
09/14/2021
Rationales for Sequential Predictions
Sequence models are a critical component of modern NLP systems, but thei...
research
∙
09/10/2021
Block Pruning For Faster Transformers
Pre-training has improved model accuracy for both classification and gen...
research
∙
09/07/2021
Datasets: A Community Library for Natural Language Processing
The scale, variety, and quantity of publicly-available NLP datasets has ...
research
∙
04/08/2021
Low-Complexity Probing via Finding Subnetworks
The dominant approach in probing neural networks for linguistic properti...
research
∙
03/15/2021
How Many Data Points is a Prompt Worth?
When fine-tuning pretrained models for classification, researchers eithe...
research
∙
02/25/2021
Named Tensor Notation
We propose a notation for tensors with named axes, which relieves the au...
research
∙
12/14/2020
Parameter-Efficient Transfer Learning with Diff Pruning
While task-specific finetuning of pretrained networks has led to signifi...
research
∙
12/02/2020
Learning from others' mistakes: Avoiding dataset biases without modeling them
State-of-the-art natural language processing (NLP) models often learn to...
research
∙
11/29/2020
Latent Template Induction with Gumbel-CRFs
Learning to control the structure of sentences is a challenging problem ...
research
∙
11/28/2020
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference
Transformer-based language models such as BERT provide significant accur...
research
∙
11/18/2020
Sequence-Level Mixed Sample Data Augmentation
Despite their empirical success, neural networks still have difficulty c...
research
∙
11/09/2020
Adversarial Semantic Collisions
We study semantic collisions: texts that are semantically unrelated but ...
research
∙
11/09/2020
Scaling Hidden Markov Language Models
The hidden Markov model (HMM) is a fundamental tool for sequence modelin...
research
∙
10/24/2020
Pre-trained Summarization Distillation
Recent state-of-the-art approaches to summarization utilize large pre-tr...
research
∙
07/10/2020
MiniConf – A Virtual Conference Framework
MiniConf is a framework for hosting virtual academic conferences motivat...
research
∙
06/01/2020
Cascaded Text Generation with Markov Transformers
The two dominant approaches to neural text generation are fully autoregr...
research
∙
05/15/2020
Movement Pruning: Adaptive Sparsity by Fine-Tuning
Magnitude pruning is a widely used strategy for reducing model size in p...
research
∙
05/10/2020
Posterior Control of Blackbox Generation
Text generation often requires high-precision output that obeys task-spe...
research
∙
05/04/2020
What is Learned in Visually Grounded Neural Syntax Acquisition
Visual features are a promising signal for learning bootstrap textual mo...
research
∙
03/13/2020
Automating Botnet Detection with Graph Neural Networks
Botnets are now a major source for many network attacks, such as DDoS at...
research
∙
02/03/2020
Torch-Struct: Deep Structured Prediction Library
The literature on structured prediction for NLP describes a rich collect...
research
∙
11/13/2019
A Hierarchy of Graph Neural Networks Based on Learnable Local Features
Graph neural networks (GNNs) are a powerful tool to learn representation...
research
∙
09/03/2019
Neural Linguistic Steganography
Whereas traditional cryptography encrypts a secret message into an unint...
research
∙
09/02/2019
Commonsense Knowledge Mining from Pretrained Models
Inferring commonsense knowledge is a key challenge in natural language p...
research
∙
08/19/2019
Encoder-Agnostic Adaptation for Conditional Language Generation
Large pretrained language models have changed the way researchers approa...
research
∙
07/31/2019
Simple Unsupervised Summarization by Contextual Matching
We propose an unsupervised method for sentence summarization using only ...
research
∙
07/24/2019
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Automation of tasks can have critical consequences when humans lose agen...
research
∙
07/09/2019
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
Popular Natural Language Inference (NLI) datasets have been shown to be ...
research
∙
07/09/2019
Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
Natural Language Inference (NLI) datasets often contain hypothesis-only ...
research
∙
06/24/2019
Compound Probabilistic Context-Free Grammars for Grammar Induction
We study a formalization of the grammar induction problem that models se...
research
∙
06/10/2019
GLTR: Statistical Detection and Visualization of Generated Text
The rapid improvement of language models has raised the specter of abuse...
research
∙
04/07/2019
Unsupervised Recurrent Neural Network Grammars
Recurrent neural network grammars (RNNG) are generative models of langua...
research
∙
01/29/2019
Latent Normalizing Flows for Discrete Sequences
Normalizing flows have been shown to be a powerful class of generative m...
research
∙
12/17/2018
A Tutorial on Deep Latent Variable Models of Natural Language
There has been much recent, exciting work on combining the complementary...
research
∙
10/10/2018