Papers with WikiSpell
English Language Spelling Correction as an Information Retrieval Task Using Wikipedia Search Statistics (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing spelling correction tools lack training or annotated data sets to perform . many spelling correction utilities suffer due to the size and quality of dictionaries available to aid correction. |
| Approach: | They propose a dynamic spelling correction tool that uses the Wikipedia dataset search API to aid misspelled term identification and automatic replacement. |
| Outcome: | The proposed spelling correction tool performs comparable to the industry-standard spelling correction algorithm, Hunspell. |
Character-Aware Models Improve Visual Text Rendering (2023.acl-long)
Copied to clipboard
Rosanne Liu, Dan Garrette, Chitwan Saharia, William Chan, Adam Roberts, Sharan Narang, Irina Blok, Rj Mical, Mohammad Norouzi, Noah Constant
| Challenge: | Current image generation models struggle to produce well-formed visual text due to lack of character-level input features. |
| Approach: | They conduct a series of experiments to compare character-aware vs. character-blind text encoders to determine their spelling ability. |
| Outcome: | The character-aware models outperform character-blind models on a range of novel text rendering tasks. |