Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909322767761408 |
|---|---|
| author | Akl, Hanna Abi |
| author_facet | Akl, Hanna Abi |
| contents | We introduce SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, and measure its performance on a knowledge base construction task using Wikidata triple completion. We evaluate SHADOW on the LM-KBC 2024 challenge and show that it outperforms the baseline solution by 20% with a F1 score of 68.72%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14849 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing Akl, Hanna Abi Computation and Language Artificial Intelligence We introduce SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, and measure its performance on a knowledge base construction task using Wikidata triple completion. We evaluate SHADOW on the LM-KBC 2024 challenge and show that it outperforms the baseline solution by 20% with a F1 score of 68.72%. |
| title | Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2408.14849 |