Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing

Autor:	Akl, Hanna Abi
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	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%. Comment: 7 pages, 1 figure, accepted for the International Conference on Natural Language Computing (NATL) 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.14849 Zobrazit plný text záznamu View this record from Arxiv