Papers by Daisuke Kihara
Protein-STORY: Semantic Text-Oriented Representation Yields biologically meaningful Protein embeddings (2026.acl-short)
Copied to clipboard
| Challenge: | Unsupervised representation learning relying on sequence data often overlooks decades of expert-curated biological knowledge stored in textual formats. |
| Approach: | They propose a pipeline that synthesizes protein embeddings from diverse, multi-source text descriptions and a network architecture that integrates high-fidelity functional and structural insights into a unified representation. |
| Outcome: | The proposed pipeline outperforms existing models on diverse downstream tasks (+2 pts F1) and enables zero-shot text-prompted protein search. |
A Gated Self-attention Memory Network for Answer Selection (D19-1)
Copied to clipboard
| Challenge: | Existing deep learning approaches for answer selection use word-level comparison followed by aggregation. |
| Approach: | They propose a new gated self-attention memory network for answer selection task . they combine a transfer learning technique from a large-scale online corpus to create a gated network . |
| Outcome: | The proposed model outperforms existing methods on two standard answer selection datasets: TrecQA and WikiQA. |