How “deep” is learning word inflection?
Open Access
- 1 January 2017
- book chapter
- Published by OpenEdition
- p. 77-82
Abstract
Machine learning offers two basic strategies for morphology induction: lexical segmentation and surface word relation. The first one assumes that words can be segmented into morphemes. Inducing a novel inflected form requires identification of morphemic constituents and a strategy for their recombination. The second approach dispenses with segmentation: lexical representations form part of a network of associatively related inflected forms. Production of a novel form consists in filling in one empty node in the network. Here, we present the results of a recurrent LSTM network that learns to fill in paradigm cells of incomplete verb paradigms. Although the process is not based on morpheme segmentation, the model shows sensitivity to stem selection and stem-ending boundaries.Keywords
This publication has 4 references indexed in Scilit:
- Regularity and/or consistency in the production of the past participle?Brain and Language, 2004
- Development of Verb Inflection in First Language Acquisition2003
- Are non-semantic morphological effects incompatible with a distributed connectionist approach to lexical processing?Language and Cognitive Processes, 2000
- Universals in Morphological Representation: Evidence from ItalianLanguage and Cognitive Processes, 1997