Cargando…
autoBOT: evolving neuro-symbolic representations for explainable low resource text classification
Learning from texts has been widely adopted throughout industry and science. While state-of-the-art neural language models have shown very promising results for text classification, they are expensive to (pre-)train, require large amounts of data and tuning of hundreds of millions or more parameters...
Autores principales: | Škrlj, Blaž, Martinc, Matej, Lavrač, Nada, Pollak, Senja |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer US
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550026/ https://www.ncbi.nlm.nih.gov/pubmed/34720391 http://dx.doi.org/10.1007/s10994-021-05968-x |
Ejemplares similares
-
Temporal Integration of Text Transcripts and Acoustic Features for Alzheimer's Diagnosis Based on Spontaneous Speech
por: Martinc, Matej, et al.
Publicado: (2021) -
Embedding-based Silhouette community detection
por: Škrlj, Blaž, et al.
Publicado: (2020) -
PubMed-Scale Chemical Concept Embeddings Reconstruct Physical Protein Interaction Networks
por: Škrlj, Blaž, et al.
Publicado: (2021) -
Propositionalization and embeddings: two sides of the same coin
por: Lavrač, Nada, et al.
Publicado: (2020) -
Investigating cross-lingual training for offensive language detection
por: Pelicon, Andraž, et al.
Publicado: (2021)