Papers with MST
Misspelling Semantics in Thai (2022.lrec-1)
Copied to clipboard
| Challenge: | In English, more than 70% of documents on the internet contain some form of misspelling . misspellers can be used as prosody to provide additional clues about the writer's attitude . |
| Approach: | They propose two ways to incorporate misspelling semantics into user-generated content . they propose a method to boost micro F1 score by 0.4-2% . |
| Outcome: | The proposed methods can boost the micro F1 score up to 0.4-2% while normalising misspelling is harmful and suboptimal. |
Colorism in Multimodal AI: An Empirical Exploration of Socioeconomic Linguistic Bias in Text-to-Image Generation (2026.eacl-srw)
Copied to clipboard
| Challenge: | Socioeconomic inequalities worldwide are deeply linked to ethnoracial hierarchies and stereotypes, argues a new study. |
| Approach: | They use a Monk Skin Tone scale to benchmark VLMs and annotators . they then use linguistic cues to vary skin-tone representations in text-to-image generation . |
| Outcome: | The study compares 3 small VLMs and 60 human annotators on the monk skin tone scale with 210 occupations and produces over 2,500 portraits across 3 large VLM models. |
MaintIE: A Fine-Grained Annotation Schema and Benchmark for Information Extraction from Maintenance Short Texts (2024.lrec-main)
Copied to clipboard
| Challenge: | Maintenance short texts (MSTs) provide crucial insights into the state and maintenance activities of machines, infrastructure, and other engineered assets. |
| Approach: | They propose a multi-level fine-grained annotation scheme for entity recognition and relation extraction that includes 5 top-level classes and 6 relations tailored to MSTs. |
| Outcome: | The proposed scheme provides high-quality, fine-grained annotations and a coarse-grain corpus of 7,000 texts. |