Simple tries and n-gram models beat large neural models for chat autocompletion on seen prefixes, while fine-tuned transformers and conversational context lead on unseen ones.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems
Simple tries and n-gram models beat large neural models for chat autocompletion on seen prefixes, while fine-tuned transformers and conversational context lead on unseen ones.