OtterlyObsessedWithSemantics at SemEval-2024 Task 4: Developing a Hierarchical Multi-Label Classification Head for Large Language Models
J. Wunderle, J. Schubert, A. Cacciatore, A. Zehe, J. Pfister, и A. Hotho. Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), стр. 602--612. Mexico City, Mexico, Association for Computational Linguistics, (июня 2024)
Аннотация
For our submission for Subtask 1, we developed a custom classification head that is designed to be applied atop of a Large Language Model. We reconstructed the hierarchy across multiple fully connected layers, allowing us to incorporate previous foundational decisions in subsequent, more fine-grained layers. To find the best hyperparameters, we conducted a grid-search and to compete in the multilingual setting, we translated all documents to English.
%0 Conference Paper
%1 wunderle-etal-2024-otterlyobsessedwithsemantics
%A Wunderle, Julia
%A Schubert, Julian
%A Cacciatore, Antonella
%A Zehe, Albin
%A Pfister, Jan
%A Hotho, Andreas
%B Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%C Mexico City, Mexico
%D 2024
%E Ojha, Atul Kr.
%E Dogruöz, A. Seza
%E Tayyar Madabushi, Harish
%E Da San Martino, Giovanni
%E Rosenthal, Sara
%E Rosá, Aiala
%I Association for Computational Linguistics
%K nlp myown motiv author:hotho author:zehe author:pfister from:janpf
%P 602--612
%T OtterlyObsessedWithSemantics at SemEval-2024 Task 4: Developing a Hierarchical Multi-Label Classification Head for Large Language Models
%U https://aclanthology.org/2024.semeval-1.90
%X For our submission for Subtask 1, we developed a custom classification head that is designed to be applied atop of a Large Language Model. We reconstructed the hierarchy across multiple fully connected layers, allowing us to incorporate previous foundational decisions in subsequent, more fine-grained layers. To find the best hyperparameters, we conducted a grid-search and to compete in the multilingual setting, we translated all documents to English.
@inproceedings{wunderle-etal-2024-otterlyobsessedwithsemantics,
abstract = {For our submission for Subtask 1, we developed a custom classification head that is designed to be applied atop of a Large Language Model. We reconstructed the hierarchy across multiple fully connected layers, allowing us to incorporate previous foundational decisions in subsequent, more fine-grained layers. To find the best hyperparameters, we conducted a grid-search and to compete in the multilingual setting, we translated all documents to English.},
added-at = {2024-07-01T03:27:07.000+0200},
address = {Mexico City, Mexico},
author = {Wunderle, Julia and Schubert, Julian and Cacciatore, Antonella and Zehe, Albin and Pfister, Jan and Hotho, Andreas},
biburl = {https://www.bibsonomy.org/bibtex/2ea37ae7d8fe363a519dce2a83864e695/dmir},
booktitle = {Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)},
editor = {Ojha, Atul Kr. and Do{\u{g}}ru{\"o}z, A. Seza and Tayyar Madabushi, Harish and Da San Martino, Giovanni and Rosenthal, Sara and Ros{\'a}, Aiala},
interhash = {07cbe0051cd36bfb2748ca112151e9ab},
intrahash = {ea37ae7d8fe363a519dce2a83864e695},
keywords = {nlp myown motiv author:hotho author:zehe author:pfister from:janpf},
month = {06},
pages = {602--612},
publisher = {Association for Computational Linguistics},
timestamp = {2024-07-01T03:27:07.000+0200},
title = {{O}tterly{O}bsessed{W}ith{S}emantics at {S}em{E}val-2024 Task 4: Developing a Hierarchical Multi-Label Classification Head for Large Language Models},
url = {https://aclanthology.org/2024.semeval-1.90},
year = 2024
}