Papers with MSEs
Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment (2025.acl-long)
Copied to clipboard
| Challenge: | Multilingual sentence encoders are often trained to map sentences from different languages into a shared semantic vector space . cross-lingual alignment training distorts optimal monolingual structure of semantic spaces of individual languages . a modular solution can be used for cross-linguistic tasks such as cross-language semantic similarity and zero-shot transfer . |
| Approach: | They propose a modular training system that embeds sentences from different languages into a shared semantic vector space. |
| Outcome: | The proposed solution achieves better performance across all tasks compared to monolithic models. |
Leveraging Language Models for Summarizing Mental State Examinations: A Comprehensive Evaluation and Dataset Release (2025.coling-main)
Copied to clipboard
| Challenge: | Mental health disorders affect a significant portion of the global population . access to mental health support is limited in developing countries . |
| Approach: | They evaluated a 12-item descriptive MSE questionnaire and five well-known summarization models . they found that language models can generate coherent MSE summaries for doctors . |
| Outcome: | The proposed model can generate coherent summaries from MSEs in a conversational format. |