conftrace_

code tokenization

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

semantic code search (1) keyword-based retrieval (1) bm25 algorithm (1) function name generation (1) source code generation (1) subword generation (1) tokenizer regularization (1) source attribution (1) natural language query (1) byte pair encoding (1)

Papers

From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution ACL 2026 Bag-of-Words Baselines for Semantic Code Search ACL 2021 Pointing to Subwords for Generating Function Names in Source Code COLING 2020