Papers by Gyu-Ho Shin
Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language Korean (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing morpheme parsers/taggers do not work reliably and optimally for L2 data. |
| Approach: | They train a neural network model on varying L2 datasets and measure its morpheme parsing/POS tagging performance on L2 test sets. |
| Outcome: | The proposed model excels in domain-specific tokenization and POS tagging compared to the baseline model. |
Constructing a Dependency Treebank for Second Language Learners of Korean (2024.lrec-main)
Copied to clipboard
| Challenge: | a manually annotated syntactic treebank is available for second language learners . the dataset includes 7,530 sentences (66,982 words; 129,333 morphemes) |
| Approach: | They propose to manually annotate syntactic treebanks based on Universal Dependencies from Korean written data. |
| Outcome: | The proposed dataset includes 7,530 sentences and 129,333 morphemes from Korean learners. |
Polysemy Interpretation and Transformer Language Models: A Case of Korean Adverbial Postposition -(u)lo (2025.coling-main)
Copied to clipboard
| Challenge: | -(u)lo is a polysemy of the Korean adverbial postposition. |
| Approach: | They analysed attention weights of a Korean pre-trained BERT model and a fine-tuned version of -(u)lo to determine their attention weight. |
| Outcome: | The attention weights of a Korean pre-trained BERT model and a fine-tuned version show a general reduction in attention weighting and changes in the lexico-phrasal information used depending on the specific function of -(u)lo. |