
-
Contrastive Explanations for Model Interpretability
Contrastive explanations clarify why an event occurred in contrast to an...
read it
-
MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation
Despite major advances in open-ended text generation, there has been lim...
read it
-
Challenges in Automated Debiasing for Toxic Language Detection
Biased associations have been a challenge in the development of classifi...
read it
-
G-DAUG: Generative Data Augmentation for Commonsense Reasoning
Recent advances in commonsense reasoning depend on large-scale human-ann...
read it
-
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
Language models pretrained on text from a wide variety of sources form t...
read it
-
The Right Tool for the Job: Matching Model and Instance Complexities
As NLP models become larger, executing a trained model requires signific...
read it
-
Adversarial Filters of Dataset Biases
Large neural models have demonstrated human-level performance on languag...
read it
-
Shallow Syntax in Deep Water
Shallow syntax provides an approximation of phrase-syntactic structure o...
read it
-
Syntactic Scaffolds for Semantic Structures
We introduce the syntactic scaffold, an approach to incorporating syntac...
read it
-
Polyglot Semantic Role Labeling
Previous approaches to multilingual semantic dependency parsing treat la...
read it
-
Learning Joint Semantic Parsers from Disjoint Data
We present a new approach to learning semantic parsers from multiple dat...
read it
-
Annotation Artifacts in Natural Language Inference Data
Large-scale datasets for natural language inference are created by prese...
read it
-
Multi-Mention Learning for Reading Comprehension with Neural Cascades
Reading comprehension is a challenging task, especially when executed ac...
read it
-
Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
We present a new, efficient frame-semantic parser that labels semantic a...
read it
-
DyNet: The Dynamic Neural Network Toolkit
We describe DyNet, a toolkit for implementing neural network models base...
read it
-
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
We present a transition-based parser that jointly produces syntactic and...
read it