# Misconceptions

20 papers with code • 1 benchmarks • 1 datasets

Measures whether a model can discern popular misconceptions from the truth.

Example:

        input: The daddy longlegs spider is the most venomous spider in the world.
choice: T
choice: F

input: Karl Benz is correctly credited with the invention of the first modern automobile.
choice: T
choice: F


Source: BIG-bench

# Community detection in networks: A user guide

Community detection in networks is one of the most popular topics of modern network science.

18

# Design Challenges and Misconceptions in Neural Sequence Labeling

We investigate the design challenges of constructing effective and efficient neural sequence labeling systems, by reproducing twelve neural sequence labeling models, which include most of the state-of-the-art structures, and conduct a systematic model comparison on three benchmarks (i. e. NER, Chunking, and POS tagging).

2

# Laplace Redux -- Effortless Bayesian Deep Learning

Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection.

2

# A Variational Inequality Perspective on Generative Adversarial Networks

Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train.

1

# Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference

5 Sep 2018

Rubric sampling requires minimal teacher effort, can associate feedback with specific parts of a student's solution and can articulate a student's misconceptions in the language of the instructor.

1

# How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions

In this work, we make the first step towards a comprehensive evaluation of cross-lingual word embeddings.

1

# Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses

Empirical research in Natural Language Processing (NLP) has adopted a narrow set of principles for assessing hypotheses, relying mainly on p-value computation, which suffers from several known issues.

1

# Deep Curvature Suite

20 Dec 2019

We present MLRG Deep Curvature suite, a PyTorch-based, open-source package for analysis and visualisation of neural network curvature and loss landscape.

1

# Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization

We show empirically that properly addressing these issues significantly improves the efficacy of linear embeddings for BO on a range of problems, including learning a gait policy for robot locomotion.

1

# On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines

Fine-tuning pre-trained transformer-based language models such as BERT has become a common practice dominating leaderboards across various NLP benchmarks.

1