On Learning Interpreted Languages with Recurrent Models | Zendy

Denis Paperno | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

On Learning Interpreted Languages with Recurrent Models

Author(s) -

Denis Paperno

Publication year - 2022

Publication title -

computational linguistics

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.314

H-Index - 98

eISSN - 1530-9312

pISSN - 0891-2017

DOI - 10.1162/coli_a_00431

Subject(s) - principle of compositionality , computer science , syntax , natural language processing , artificial intelligence , semantics (computer science) , construct (python library) , recurrent neural network , interpretation (philosophy) , programming language , artificial neural network

Can recurrent neural nets, inspired by human sequential data processing, learn to understand language? We construct simplified data sets reflecting core properties of natural language as modeled in formal syntax and semantics: recursive syntactic structure and compositionality. We find LSTM and GRU networks to generalize to compositional interpretation well, but only in the most favorable learning settings, with a well-paced curriculum, extensive training data, and left-to-right (but not right-to-left) composition.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research