Rethinking Loss Functions for Fact Verification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917611925667840 |
|---|---|
| author | Mukobara, Yuta Shigeto, Yutaro Shimbo, Masashi |
| author_facet | Mukobara, Yuta Shigeto, Yutaro Shimbo, Masashi |
| contents | We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy. Performance is further improved when these objectives are combined with simple class weighting, which effectively overcomes the imbalance in the training data. The souce code is available at https://github.com/yuta-mukobara/RLF-KGAT |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Loss Functions for Fact Verification Mukobara, Yuta Shigeto, Yutaro Shimbo, Masashi Computation and Language Artificial Intelligence We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this paper, we develop two task-specific objectives tailored to FEVER. Experimental results confirm that the proposed objective functions outperform the standard cross-entropy. Performance is further improved when these objectives are combined with simple class weighting, which effectively overcomes the imbalance in the training data. The souce code is available at https://github.com/yuta-mukobara/RLF-KGAT |
| title | Rethinking Loss Functions for Fact Verification |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.08174 |