activity
20182022
most citedFusing finetuned models for better pretraining

12 citations · 27 across the 7 of their papers we have counts for

collaborators

21 papers

cs.CL2022

Some Grammatical Errors are Frequent, Others are Important

Leshem Choshen, Ofir Shifman, Omri Abend

In Grammatical Error Correction, systems are evaluated by the number of errors they correct. However, no one has assessed whether all error types are equally important. We provide…

cs.CL202212 cited

Fusing finetuned models for better pretraining

Leshem Choshen, Elad Venezian, Noam Slonim +1

Pretrained models are the standard starting point for training. This approach consistently outperforms the use of a random initialization. However, pretraining is a costly endeavou…

cs.CL20221 cited

Cluster & Tune: Boost Cold Start Performance in Text Classification

Eyal Shnarch, Ariel Gera, Alon Halfon +4

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 model…

cs.CL20211 cited

ComSum: Commit Messages Summarization and Meaning Preservation

Leshem Choshen, Idan Amit

We present ComSum, a data set of 7 million commit messages for text summarization. When documenting commits, software code changes, both a message and its summary are posted. We ga…

cs.CL20212 cited

Part of Speech and Universal Dependency effects on English Arabic Machine Translation

Ofek Rafaeli, Omri Abend, Leshem Choshen +1

In this research paper, I will elaborate on a method to evaluate machine translation models based on their performance on underlying syntactical phenomena between English and Arabi…

cs.CL20218 cited

SERRANT: a syntactic classifier for English Grammatical Error Types

Leshem Choshen, Matanel Oren, Dmitry Nikolaev +1

SERRANT is a system and code for automatic classification of English grammatical errors that combines SErCl and ERRANT. SERRANT uses ERRANT's annotations when they are informative…