1 code implementation • 25 Jan 2024 • Elron Bandel, Yotam Perlitz, Elad Venezian, Roni Friedman-Melamed, Ofir Arviv, Matan Orbach, Shachar Don-Yehyia, Dafna Sheinwald, Ariel Gera, Leshem Choshen, Michal Shmueli-Scheuer, Yoav Katz
In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, and model combinations.
no code implementations • 25 Jan 2024 • Asaf Yehudai, Boaz Carmeli, Yosi Mass, Ofir Arviv, Nathaniel Mills, Assaf Toledo, Eyal Shnarch, Leshem Choshen
Furthermore, we compare models trained on our data with models trained on human-written data -- ELI5 and ASQA for LFQA and CNN-DailyMail for Summarization.
1 code implementation • 20 Oct 2023 • Ofir Arviv, Dmitry Nikolaev, Taelin Karidi, Omri Abend
Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource setting.
no code implementations • 22 Aug 2023 • Yotam Perlitz, Elron Bandel, Ariel Gera, Ofir Arviv, Liat Ein-Dor, Eyal Shnarch, Noam Slonim, Michal Shmueli-Scheuer, Leshem Choshen
Based on our findings we outline a set of concrete recommendations for more efficient benchmark design and utilization practices leading to dramatic cost savings with minimal loss of benchmark reliability often reducing computation by x100 or more.
1 code implementation • 2 May 2023 • Ariel Gera, Roni Friedman, Ofir Arviv, Chulaka Gunasekara, Benjamin Sznajder, Noam Slonim, Eyal Shnarch
Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative.
1 code implementation • EMNLP 2021 • Ofir Arviv, Dmitry Nikolaev, Taelin Karidi, Omri Abend
We explore the link between the extent to which syntactic relations are preserved in translation and the ease of correctly constructing a parse tree in a zero-shot setting.
no code implementations • CONLL 2020 • Ofir Arviv, Ruixiang Cui, Daniel Hershcovich
This paper describes the HUJI-KU system submission to the shared task on CrossFramework Meaning Representation Parsing (MRP) at the 2020 Conference for Computational Language Learning (CoNLL), employing TUPA and the HIT-SCIR parser, which were, respectively, the baseline system and winning system in the 2019 MRP shared task.
no code implementations • 12 Oct 2020 • Ofir Arviv, Ruixiang Cui, Daniel Hershcovich
This paper describes the HUJI-KU system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2020 Conference for Computational Language Learning (CoNLL), employing TUPA and the HIT-SCIR parser, which were, respectively, the baseline system and winning system in the 2019 MRP shared task.
Ranked #2 on Semantic Parsing on DRG (english, MRP 2020)
1 code implementation • ACL 2020 • Dmitry Nikolaev, Ofir Arviv, Taelin Karidi, Neta Kenneth, Veronika Mitnik, Lilja Maria Saeboe, Omri Abend
The patterns in which the syntax of different languages converges and diverges are often used to inform work on cross-lingual transfer.
no code implementations • CONLL 2019 • Daniel Hershcovich, Ofir Arviv
This paper describes the TUPA system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).
Ranked #2 on UCCA Parsing on CoNLL 2019