Papers by Takuto Asakura
What Is Needed for Intra-document Disambiguation of Math Identifiers? (2024.lrec-main)
Copied to clipboard
| Challenge: | Ambiguity in math identifiers within a document poses significant challenges to understanding formulae . ambiguity in mathematical expressions can be difficult to disambiguate, requiring intra-document disambiguation . |
| Approach: | They propose to use position data and local formula structure to disambiguate math identifiers . they train a model that performs similarly to humans with an 85% accuracy . |
| Outcome: | The proposed model outperforms rule-based models in natural language processing. |
Building Dataset for Grounding of Formulae — Annotating Coreference Relations Among Math Identifiers (2022.lrec-1)
Copied to clipboard
| Challenge: | Generally speaking, the meanings of math symbols are not necessarily constant, and the same symbol is used in multiple meanings. |
| Approach: | They annotated 15 papers with the meanings of math symbols and found they can be grounding . they developed a special annotation tool to help them identify the meaning of each symbol . |
| Outcome: | The constructed dataset shows that the meanings of symbols can be ground with a high agreement . the authors developed a special annotation tool to analyze the data . |
Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement (2026.acl-industry)
Copied to clipboard
Wataru Hirota, Tomoki Taniguchi, Tomoko Ohkuma, Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Takuto Asakura, Chung-Chi Chen, Tatsuya Ishigaki
| Challenge: | Large language models (LLMs) make it easy to generate large numbers of product ideas. |
| Approach: | They propose to use a dataset of 3,000 individual scores across 300 patent-grounded product ideas to assess whether an automatic judge approximates an aggregate consensus. |
| Outcome: | The proposed model evaluators disagree on fine-grained ordinal scores, suggesting structured heterogeneity rather than random noise. |