NLPExplorer

BlackboxNLP - 2021

Total Papers:- 44

Total Papers accross all years:- 107

Total Citations :- 0

« 1 2 3

Multi-Layer Random Perturbation Training for improving Model Generalization Efficiently

Lis Kanashiro Pereira | Yuki Taya | Ichiro Kobayashi |

To what extent do human explanations of model behavior align with actual model behavior?

Test Harder than You Train: Probing with Extrapolation Splits

Jenny Kunz | Marco Kuhlmann |

Exploratory Model Analysis Using Data-Driven Neuron Representations

Daisuke Oba | Naoki Yoshinaga | Masashi Toyoda |

How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings

Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN

Rahma Chaabouni | Roberto Dessì | Eugene Kharitonov |

Analyzing BERT’s Knowledge of Hypernymy via Prompting

Michael Hanna | David Mareček |

A howling success or a working sea? Testing what BERT knows about metaphors

Paolo Pedinotti | Eliana Di Palma | Ludovica Cerini | Alessandro Lenci |

Learning Mathematical Properties of Integers

Maria Ryskina | Kevin Knight |

Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers

Jason Phang | Haokun Liu | Samuel R. Bowman |

An Investigation of Language Model Interpretability via Sentence Editing

Samuel Stevens | Yu Su |

Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations

The Acceptability Delta Criterion: Testing Knowledge of Language using the Gradience of Sentence Acceptability

Héctor Vázquez Martínez |