Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Pereg, Oren"'
Autor:
Timor, Nadav, Mamou, Jonathan, Korat, Daniel, Berchansky, Moshe, Pereg, Oren, Wasserblat, Moshe, Galanti, Tomer, Gordon, Michal, Harel, David
Accelerating the inference of large language models (LLMs) is an important challenge in artificial intelligence. This paper introduces Distributed Speculative Inference (DSI), a novel distributed inference algorithm that is provably faster than specu
Externí odkaz:
http://arxiv.org/abs/2405.14105
Autor:
Mamou, Jonathan, Pereg, Oren, Korat, Daniel, Berchansky, Moshe, Timor, Nadav, Wasserblat, Moshe, Schwartz, Roy
Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of tokens generated by the draft model at each iteration. In this work we
Externí odkaz:
http://arxiv.org/abs/2405.04304
Autor:
Howard, Phillip, Ma, Arden, Lal, Vasudev, Simoes, Ana Paula, Korat, Daniel, Pereg, Oren, Wasserblat, Moshe, Singer, Gadi
Publikováno v:
Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM 2022). Association for Computing Machinery, New York, NY, USA, 780-790
The extraction of aspect terms is a critical step in fine-grained sentiment analysis of text. Existing approaches for this task have yielded impressive results when the training and testing data are from the same domain. However, these methods show a
Externí odkaz:
http://arxiv.org/abs/2210.10144
Autor:
Tunstall, Lewis, Reimers, Nils, Jo, Unso Eun Seo, Bates, Luke, Korat, Daniel, Wasserblat, Moshe, Pereg, Oren
Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high variability
Externí odkaz:
http://arxiv.org/abs/2209.11055
The remarkable success of large transformer-based models such as BERT, RoBERTa and XLNet in many NLP tasks comes with a large increase in monetary and environmental cost due to their high computational load and energy consumption. In order to reduce
Externí odkaz:
http://arxiv.org/abs/2204.06271
We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction. The system is interpretable and user friendly and does not require labeled training data, hence can be rapidly and cost-effectively used across different do
Externí odkaz:
http://arxiv.org/abs/1909.05608
In this paper, we present a novel algorithm that combines multi-context term embeddings using a neural classifier and we test this approach on the use case of corpus-based term set expansion. In addition, we present a novel and unique dataset for int
Externí odkaz:
http://arxiv.org/abs/1904.02496
Autor:
Mamou, Jonathan, Pereg, Oren, Wasserblat, Moshe, Eirew, Alon, Green, Yael, Guskin, Shira, Izsak, Peter, Korat, Daniel
We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed
Externí odkaz:
http://arxiv.org/abs/1808.08953
Autor:
Mamou, Jonathan, Pereg, Oren, Wasserblat, Moshe, Dagan, Ido, Goldberg, Yoav, Eirew, Alon, Green, Yael, Guskin, Shira, Izsak, Peter, Korat, Daniel
We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to end workflow for term set expansion. It enables users
Externí odkaz:
http://arxiv.org/abs/1807.10104