On Learning Interpreted Languages with Recurrent Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Limitations in learning an interpreted language with recurrent models
There is no fast lunch: an examination of the running speed of evolutionary algorithms in several languages
It is quite usual when an evolutionary algorithm tool or library uses a language other than C, C++, Java or Matlab that a reviewer or the audience questions its usefulness based on the speed of those other languages, pur…
Evolutionary AlgorithmsParsing Minimalist Languages with Interpreted Regular Tree Grammars
Recent Advances in SQL Query Generation: A Survey
Natural language is hypothetically the best user interface for many domains. However, general models that provide an interface between natural language and any other domain still do not exist. Providing natural language …
SurveyOn the Expressivity of Recurrent Neural Cascades with Identity
Recurrent Neural Cascades (RNC) are the class of recurrent neural networks with no cyclic dependencies among recurrent neurons. Their subclass RNC+ with positive recurrent weights has been shown to be closely connected t…