: NLP Vocabulary: EARL

NLP methods and tools > NLP software > EARL

EARL

As shown in Table 3 EARL obtains the best performances in most metrics on all the test sets demonstrating that EARL can generate more informative relevant and diverse responses than baseline models based on both trained and untrained knowledge graphs. (Zhou, Huang, Liu, Chen & Zhu, 2021)
Besides EARL outperforms all the baselines in the Precision Recall and F1 metrics showing that entities selected by EARL are more relevant to the ground-truth entities. (Zhou, Huang, Liu, Chen & Zhu, 2021)
EARL consists of three modules: an encoder to convert the context to the hidden representations a knowledge interpreter to represent each subject and object entity based on the context and structure information and a decoder to generate a token or select an entity from the knowledge graph determined by a knowledge selector. (Zhou, Huang, Liu, Chen & Zhu, 2021)
However EARL achieves comparable performances on the unseen test set even most scores are slightly higher than those on the seen test set indicating that EARL can utilize the unseen entities in knowledge graphs during the inference process. (Zhou, Huang, Liu, Chen & Zhu, 2021)
Specifically EARL achieves the highest number of entities per generated response which is nearly two times higher than the second-highest score obtained by CCM indicating that EARL is able to generate more informative responses. (Zhou, Huang, Liu, Chen & Zhu, 2021)

http://data.loterre.fr/ark:/67375/8LP-Q4T501RR-V

RDF/XML TURTLE JSON-LD Last modified 5/3/24

Loterre