Papers by Ivan Yamshchikov
BERT in Plutarch’s Shadows (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to estimate authorship of texts rely on statistical patterns like word or sentence length to distinguish between different authors. |
| Approach: | They propose to use a BERT language model to identify authorship in ancient Greek texts . they find that the Placita Philosophorum and other works are similar to those written by Alexandrian authors . |
| Outcome: | The proposed model can shed new light on the authorship question in ancient Greek and shows similarities with the works written by authors from Alexandrian contexts. |
BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training (2024.emnlp-main)
Copied to clipboard
| Challenge: | Tokenization is a relatively understudied area, but it can greatly impact model performance and efficiency. |
| Approach: | They propose a modified BPE tokenizer that removes merges that leave intermediate "junk" tokens from the vocabulary. |
| Outcome: | The proposed method improves vocabulary efficiency, eliminates under-trained tokens, and does not compromise text compression. |