Logo Logo
Switch Language to German

Hofmann, Valentin; Schütze, Hinrich and Pierrehumbert, Janet (6. July 2020): A Graph Auto-encoder Model of Derivational Morphology. UNSPECIFIED, July 6 – 8, 2020, Seattle, USA [PDF, 1MB]

[thumbnail of Hofmann_etal_DGA_ACL2020.pdf]
Download (1MB)


There has been little work on modeling the morphological well-formedness (MWF) of derivatives, a problem judged to be complex and difficult in linguistics (Bauer, 2019). We present a graph auto-encoder that learns em- beddings capturing information about the com- patibility of affixes and stems in derivation. The auto-encoder models MWF in English sur- prisingly well by combining syntactic and se- mantic information with associative informa- tion from the mental lexicon.

Actions (login required)

View Item View Item