We propose N e s t e r, a method for injecting neural networks into constrained structured predictors. N e s t e r first uses a neural network to compute an initial prediction that may or may not satisfy the constraints, and then applies a constraint-based structured predictor to refine the raw predictions according to hard and soft constraints. N e s t e r combines the advantages of its two components: the network can learn complex representations from low-level data while the constraint program on top reasons about the high-level properties and requirements of the prediction task. An empirical evaluation on handwritten equation recognition shows that N e s t e r achieves better performance than both the either component in isolation, especially when training examples are scarce, while scaling to more complex problems than other neuro-programming approaches. N e s t e r proves especially useful to reduce errors at the semantic level of the problem, which is particularly challenging for neural network architectures.
Neuro-Symbolic Constraint Programming for Structured Prediction / Dragone, Paolo; Teso, Stefano; Passerini, Andrea. - 2986:(2021), pp. 6-14. (Intervento presentato al convegno 15th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2021 tenutosi a virtual nel 25-27 October 2021).
Neuro-Symbolic Constraint Programming for Structured Prediction
Dragone, Paolo;Teso, Stefano;Passerini, Andrea
2021-01-01
Abstract
We propose N e s t e r, a method for injecting neural networks into constrained structured predictors. N e s t e r first uses a neural network to compute an initial prediction that may or may not satisfy the constraints, and then applies a constraint-based structured predictor to refine the raw predictions according to hard and soft constraints. N e s t e r combines the advantages of its two components: the network can learn complex representations from low-level data while the constraint program on top reasons about the high-level properties and requirements of the prediction task. An empirical evaluation on handwritten equation recognition shows that N e s t e r achieves better performance than both the either component in isolation, especially when training examples are scarce, while scaling to more complex problems than other neuro-programming approaches. N e s t e r proves especially useful to reduce errors at the semantic level of the problem, which is particularly challenging for neural network architectures.File | Dimensione | Formato | |
---|---|---|---|
deep_pyconstruct___nesy21.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
839.23 kB
Formato
Adobe PDF
|
839.23 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione