Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Gera, Ariel"'
Autor:
Perlitz, Yotam, Gera, Ariel, Arviv, Ofir, Yehudai, Asaf, Bandel, Elron, Shnarch, Eyal, Shmueli-Scheuer, Michal, Choshen, Leshem
Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is assessing the validity of the benchmarks themselves. This is most comm
Externí odkaz:
http://arxiv.org/abs/2407.13696
Autor:
Ashury-Tahan, Shir, Gera, Ariel, Sznajder, Benjamin, Choshen, Leshem, Ein-Dor, Liat, Shnarch, Eyal
Model selection for a given target task can be costly, as it may entail extensive annotation of the quality of outputs of different models. We introduce DiffUse, an efficient method to make an informed decision between candidate text generation model
Externí odkaz:
http://arxiv.org/abs/2402.07891
Autor:
Bandel, Elron, Perlitz, Yotam, Venezian, Elad, Friedman-Melamed, Roni, Arviv, Ofir, Orbach, Matan, Don-Yehyia, Shachar, Sheinwald, Dafna, Gera, Ariel, Choshen, Leshem, Shmueli-Scheuer, Michal, Katz, Yoav
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. The escalating complexity, involving system prom
Externí odkaz:
http://arxiv.org/abs/2401.14019
Autor:
Perlitz, Yotam, Bandel, Elron, Gera, Ariel, Arviv, Ofir, Ein-Dor, Liat, Shnarch, Eyal, Slonim, Noam, Shmueli-Scheuer, Michal, Choshen, Leshem
The increasing versatility of language models (LMs) has given rise to a new class of benchmarks that comprehensively assess a broad range of capabilities. Such benchmarks are associated with massive computational costs, extending to thousands of GPU
Externí odkaz:
http://arxiv.org/abs/2308.11696
Autor:
Perlitz, Yotam, Gera, Ariel, Shmueli-Scheuer, Michal, Sheinwald, Dafna, Slonim, Noam, Ein-Dor, Liat
The field of Natural Language Generation (NLG) suffers from a severe shortage of labeled data due to the extremely expensive and time-consuming process involved in manual annotation. A natural approach for coping with this problem is active learning
Externí odkaz:
http://arxiv.org/abs/2305.15040
Autor:
Gera, Ariel, Friedman, Roni, Arviv, Ofir, Gunasekara, Chulaka, Sznajder, Benjamin, Slonim, Noam, Shnarch, Eyal
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. In this work, we argue that due to the g
Externí odkaz:
http://arxiv.org/abs/2305.01628
Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to their promi
Externí odkaz:
http://arxiv.org/abs/2210.17541
Autor:
Shnarch, Eyal, Halfon, Alon, Gera, Ariel, Danilevsky, Marina, Katsis, Yannis, Choshen, Leshem, Cooper, Martin Santillan, Epelboim, Dina, Zhang, Zheng, Wang, Dakuo, Yip, Lucy, Ein-Dor, Liat, Dankin, Lena, Shnayderman, Ilya, Aharonov, Ranit, Li, Yunyao, Liberman, Naftali, Slesarev, Philip Levin, Newton, Gwilym, Ofek-Koifman, Shila, Slonim, Noam, Katz, Yoav
Text classification can be useful in many real-world scenarios, saving a lot of time for end users. However, building a custom classifier typically requires coding skills and ML knowledge, which poses a significant barrier for many potential users. T
Externí odkaz:
http://arxiv.org/abs/2208.01483
Autor:
Shnarch, Eyal, Gera, Ariel, Halfon, Alon, Dankin, Lena, Choshen, Leshem, Aharonov, Ranit, Slonim, Noam
In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce. In such cases, the common practice of fine-tuning pre-trained models, such as BERT, for a target classification task, is prone to produce
Externí odkaz:
http://arxiv.org/abs/2203.10581
Autor:
Ein-Dor, Liat, Gera, Ariel, Toledo-Ronen, Orith, Halfon, Alon, Sznajder, Benjamin, Dankin, Lena, Bilu, Yonatan, Katz, Yoav, Slonim, Noam
Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more recent works employing machine learning techniques. This work is in line with this latter approach, leveraging relevant Wikipedi
Externí odkaz:
http://arxiv.org/abs/1911.10783