activity
20182022
most citedAugmented Natural Language for Generative Sequence Labeling

3 citations · 5 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL20221 cited

Label Semantic Aware Pre-training for Few-shot Text Classification

Aaron Mueller, Jason Krone, Salvatore Romeo +4

In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification perfor…

cs.CL20211 cited

Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer

Weijia Xu, Batool Haider, Jason Krone +1

Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effectiv…

cs.CL2021

On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise

Sailik Sengupta, Jason Krone, Saab Mansour

Intent Classification (IC) and Slot Labeling (SL) models, which form the basis of dialogue systems, often encounter noisy data in real-word environments. In this work, we investiga…

cs.CL2020

Meta learning to classify intent and slot labels with noisy few shot examples

Shang-Wen Li, Jason Krone, Shuyan Dong +2

Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU). However, deep learning models are notorious for being data-hungry,…

cs.CL20203 cited

Augmented Natural Language for Generative Sequence Labeling

Ben Athiwaratkun, Cicero Nogueira dos Santos, Jason Krone +1

We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared…

cs.CL2020

Learning to Classify Intents and Slot Labels Given a Handful of Examples

Jason Krone, Yi Zhang, Mona Diab

Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training example…