Theoretical and Empirical Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Open-World Scenarios

Theoretical and Empirical Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Open-World Scenarios Paulo Cavalin author Claudio Santos Pinhanez author 2024-05 text Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) Nicoletta Calzolari editor Min-Yen Kan editor Veronique Hoste editor Alessandro Lenci editor Sakriani Sakti editor Nianwen Xue editor ELRA and ICCL Torino, Italia conference publication cavalin-pinhanez-2024-theoretical https://aclanthology.org/2024.lrec-main.1391/ 2024-05 16000 16013