publication

“X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents”
- Sotaro Takeshita, Tommaso Green, Niklas Friedrich, Kai Eckert and Simone Paolo Ponzetto
- ACM/IEEE Joint Conference on Digital Libraries (JCDL), 2022 / paper / code / data
- tl;dr: Dataset for papers in en to summaries in (de/it/zh/ja).
“ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System”
- Chia-Chien Hung, Tommaso Green, Robert Litschko, Tornike Tsereteli, Sotaro Takeshita, Marco Bombieri, Goran Glavaš, Simone Paolo Ponzetto
- NAACL 2022 - MIA shared-task / pdf / code
- tl;dr: Cross-lingual QA is hard.
“Cross-lingual extreme summarization of scholarly documents”
- Sotaro Takeshita, Tommaso Green, Niklas Friedrich, Kai Eckert and Simone Paolo Ponzetto
- International Journal on Digital Libraries / 2023 / paper / code / data
- tl;dr: publishing a journal paper takes time
“ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications”
- Sotaro Takeshita, Tommaso Green, Ines Reinig, Kai Eckert and Simone Paolo Ponzetto
- NAACL 2024 / pdf / data
- tl;dr: annotation for summarization task take a lot of time
“ROUGE-K: Do Your Summaries Have Keywords?”
- Sotaro Takeshita, Simone Paolo Ponzetto, Kai Eckert
- *SEM 2024, Best Long Paper / pdf
- tl;dr: what is keyword?
“GenGO: ACL Paper Explorer with Semantic Features”
- Sotaro Takeshita, Simone Paolo Ponzetto, Kai Eckert
- To appear at ACL System demonstrations 2024
- ACL 2024 SDT / paper / system
- tl;dr: keep running ML app cheaply is hard
“GenGO Ultra: an LLM-powered ACL Paper Explorer”
- Sotaro Takeshita, Tornike Tsereteli, Simone Paolo Ponzetto
- To appear at ACL System demonstrations 2025, system
- tl;dr: keep running LLM app cheaply is even harder
“IRSum: One Model to Rule Summarization and Retrieval”
- Sotaro Takeshita, Simone Paolo Ponzetto, Kai Eckert
- To appear at GEM Workshop at ACL 2025
- tl;dr: now we don’t have to process the same document twice