3 papers
cs.CL2023
Finite-context Indexing of Restricted Output Space for NLP Models Facing Noisy Input
Minh Nguyen, Nancy F. Chen
NLP models excel on tasks with clean inputs, but are less accurate with noisy inputs. In particular, character-level noise such as human-written typos and adversarially-engineered…
cs.CL2020
Domain-shift Conditioning using Adaptable Filtering via Hierarchical Embeddings for Robust Chinese Spell Check
Minh Nguyen, Gia H. Ngo, Nancy F. Chen
Spell check is a useful application which processes noisy human-generated text. Spell check for Chinese poses unresolved problems due to the large number of characters, the sparse…
cs.CL2019
Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin using Recursive Neural Networks
Minh Nguyen, Gia H. Ngo, Nancy F. Chen
Logographs (Chinese characters) have recursive structures (i.e. hierarchies of sub-units in logographs) that contain phonological and semantic information, as developmental psychol…