In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of Semeval Task 2 of emoji prediction (Barbieri et al., 2018). The model builds on the distributed tree embedder also known as distributed tree kernel (Zanzotto and Dell'Arciprete, 2012). Initial results are extremely encouraging but additional analysis is needed to overcome the problem of overfitting.
SyntNN at SemEval-2018 Task 2: Is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons / Santilli, A.; Zanzotto, F. M.. - (2018), pp. 477-481. (Intervento presentato al convegno NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop tenutosi a New Orleans; USA).
SyntNN at SemEval-2018 Task 2: Is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons
Santilli A.Primo
;
2018
Abstract
In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of Semeval Task 2 of emoji prediction (Barbieri et al., 2018). The model builds on the distributed tree embedder also known as distributed tree kernel (Zanzotto and Dell'Arciprete, 2012). Initial results are extremely encouraging but additional analysis is needed to overcome the problem of overfitting.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
