MaChAmp at SemEval-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic Datasets

Rob van der Goot


Abstract
Previous work on multi-task learning in Natural Language Processing (NLP) oftenincorporated carefully selected tasks as well as carefully tuning ofarchitectures to share information across tasks. Recently, it has shown thatfor autoregressive language models, a multi-task second pre-training step on awide variety of NLP tasks leads to a set of parameters that more easily adaptfor other NLP tasks. In this paper, we examine whether a similar setup can beused in autoencoder language models using a restricted set of semanticallyoriented NLP tasks, namely all SemEval 2022 tasks that are annotated at theword, sentence or paragraph level. We first evaluate a multi-task model trainedon all SemEval 2022 tasks that contain annotation on the word, sentence orparagraph level (7 tasks, 11 sub-tasks), and then evaluate whetherre-finetuning the resulting model for each task specificially leads to furtherimprovements. Our results show that our mono-task baseline, our multi-taskmodel and our re-finetuned multi-task model each outperform the other modelsfor a subset of the tasks. Overall, huge gains can be observed by doingmulti-task learning: for three tasks we observe an error reduction of more than40%.
Anthology ID:
2022.semeval-1.233
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1695–1703
Language:
URL:
https://aclanthology.org/2022.semeval-1.233
DOI:
10.18653/v1/2022.semeval-1.233
Bibkey:
Cite (ACL):
Rob van der Goot. 2022. MaChAmp at SemEval-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic Datasets. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1695–1703, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
MaChAmp at SemEval-2022 Tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task Multi-lingual Learning for a Pre-selected Set of Semantic Datasets (van der Goot, SemEval 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.semeval-1.233.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2022.semeval-1.233.mp4
Code
 robvanderg/semeval2022
Data
GLUE