conftrace_

character-level processing

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) text classification (2) natural language processing (2) deep convolutional network (1) text normalization (1) neural text normalization (1) language diversity (1) character window (1) language span identification (1) character-level convolution (1)

Papers

Beyond the Spelling Miracle: Investigating Substring Awareness in Character-Blind Language Models ACL 2025 EXECUTE: A Multilingual Benchmark for LLM Token Understanding ACL 2025 Preserving Comorian Linguistic Heritage: Bidirectional Transliteration Between the Latin Alphabet and the Kamar-Eddine System NAACL 2025 Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Characters EMNLP 2025 Large Language Models Can Not Perform Well in Understanding and Manipulating Natural Language at Both Character and Word Levels? EMNLP 2024 Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text EMNLP 2023 Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels IJCNLP 2017 LanideNN: Multilingual Language Identification on Character Window EACL 2017 Very Deep Convolutional Networks for Text Classification EACL 2017 Improving historical spelling normalization with bi-directional LSTMs and multi-task learning COLING 2016