NLPExplorer

Michael Hanna

Number of Papers:- 10

Number of Citations:- 0

First ACL Paper:- 2021

Latest ACL Paper:- 2024

Venues:-

s

EMNLP

i

d

-

A

WS

CoNLL

L

BlackboxNLP

C

COLING

EACL

RepL4NLP

WMT

F

n

g

Co-Authors:-

Abhijith Chintam

Alberto Testoni

Alessandro Suglia

Similar Authors:-

Transformer-specific Interpretability EACL

Hosein Mohebbi | Jaap Jumelet | Michael Hanna | Afra Alishahi | Willem Zuidema |

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST! F i n d i n g s - A C L

Frank Wildenburg | Michael Hanna | Sandro Pezzelle |

LLM Circuit Analyses Are Consistent Across Training and Scale RepL4NLP WS

Curt Tigges | Michael Hanna | Qinan Yu | Stella Biderman |

The Functional Relevance of Probed Information: A Case Study EACL

Michael Hanna | Roberto Zamparelli | David Mareček |

When Language Models Fall in Love: Animacy Processing in Transformer Language Models EMNLP

Michael Hanna | Yonatan Belinkov | Sandro Pezzelle |

Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model BlackboxNLP WS

Abhijith Chintam | Rahel Beloch | Willem Zuidema | Michael Hanna | Oskar van der Wal |

ChapGTP, ILLC’s Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation CoNLL

Jaap Jumelet | Michael Hanna | Marianne de Heer Kloots | Anna Langedijk | Charlotte Pouw | Oskar van der Wal |

ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments COLING

Michael Hanna | Federico Pedeni | Alessandro Suglia | Alberto Testoni | Raffaella Bernardi |

A Fine-Grained Analysis of BERTScore EMNLP WMT

Michael Hanna | Ondřej Bojar |

Analyzing BERT’s Knowledge of Hypernymy via Prompting BlackboxNLP EMNLP

Michael Hanna | David Mareček |

.