Neural Networks and Quantifier Conservativity: Does Data Distribution Affect Learnability?
All known natural language determiners are conservative. Psycholinguistic experiments indicate that children exhibit a corresponding learnability bias when faced with the task of learning new determiners. However, recent work indicates that this bias towards conservativity is not observed during the training stage of artificial neural networks. In this work, we investigate whether the learnability bias exhibited by children is in part due to the distribution of quantifiers in natural language. We share results of five experiments, contrasted by the distribution of conservative vs. non-conservative determiners in the training data. We demonstrate that the aquisitional issues with non-conservative quantifiers can not be explained by the distribution of natural language data, which favors conservative quantifiers. This finding indicates that the bias in language acquisition data might be innate or representational.
Code (0)
등록된 구현이 없습니다.
Tasks
Language AcquisitionSimilar Papers 제목 키워드 기반
Compositionality and the lexicon in evolutionary semantics
Formal semantics has shown that sentence meanings arise by recursively composing lexical meanings, yet much of the literature on semantic universals models either lexicons with fixed signal structures or holistic composi…
Quantifier Scope in Categorical Compositional Distributional Semantics
In previous work with J. Hedges, we formalised a generalised quantifiers theory of natural language in categorical compositional distributional semantics with the help of bialgebras. In this paper, we show how quantifier…
Fuzzy Generalised Quantifiers for Natural Language in Categorical Compositional Distributional Semantics
Recent work on compositional distributional models shows that bialgebras over finite dimensional vector spaces can be applied to treat generalised quantifiers for natural language. That technique requires one to construc…
Continuous Sweep for Binary Quantification Learning
A quantifier is a supervised machine learning algorithm, focused on estimating the class prevalence in a dataset rather than labeling its individual observations. We introduce Continuous Sweep, a new parametric binary qu…
Binary QuantificationAn Annotation Scheme for Quantifier Scope Disambiguation
Annotating natural language sentences with quantifier scoping has proved to be very hard. In order to overcome the challenge, previous work on building scope-annotated corpora has focused on sentences with two explicitly…
Semantic ParsingSentence