research
∙
02/04/2023
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
When upgrading neural models to a newer version, new errors that were no...
share
research
∙
01/25/2023
Backward Compatibility During Data Updates by Weight Interpolation
Backward compatibility of model predictions is a desired property when u...
research
∙
02/07/2022
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
Recent advance in deep learning has led to rapid adoption of machine lea...
research
∙
09/29/2021
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Pre-trained language models have been recently shown to benefit task-ori...
research
∙
09/15/2021
Efficient Domain Adaptation of Language Models via Adaptive Tokenization
Contextual embedding-based language models trained on large data sets, s...
research
∙
05/07/2021
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Behavior of deep neural networks can be inconsistent between different v...
research
∙
03/19/2020
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
Summarizing data samples by quantitative measures has a long history, wi...
research
∙
09/19/2019
Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation
Hierarchical neural networks are often used to model inherent structures...
research
∙
10/20/2018