Publications

Semantic | Google Scholar Tweeter: LChoshen 

• Leshem Choshen, Matanel Orenm Dmitry Nikolaev, Omri Abend (ArXiv - technical report) SERRANT: a syntactic classifier for English Grammatical Error Types
  [bib][pdf][code][Latex]

• Aviv Solobodkin, Leshem Choshen, Omri Abend (NAACL2021) Mediators in Determining what Processing BERT Performs First
  [bib][pdf][code][Latex]

• Project Debater - an Autonomous Debating System (Nature 2021 cover)
  [bib][pdf][code][Latex]

• Leshem Choshen, Dmitry Nikolaev, Yevgeni Berzak, Omri Abend (CoNLL 2020) Classifying Syntactic Errors in Learner Language
  [bib][pdf][code][Latex]

• Eyal Shnarch, Leshem Choshen,* Guy Moshkowich, Ranit Aharonov, Noam Slonim (EMNLP 2020) Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains
  [bib][pdf][code][Latex]

• Guy Hacohen, Leshem Choshen, Daphna Weinshall (ICML 2020) Let's agree to agree: neural networks share classification order on real datasets
  [bib][pdf][code][Latex]

• Leshem Choshen, Lior Fox, Zohar Aizenbud, Omri Abend (ICLR 2020) On the Weaknesses of Reinforcement Learning for Neural Machine Translation
  [bib] [pdf] [code] [Latex] 

• Liat Ein-Dor, Eyal Shnarch, Lena Dankin, Alon Halfon, Benjamin Sznajder, Ariel Gera, Carlos Alzate, Martin Gleize, Leshem Choshen, Yufang Hou, Yonatan Bilu, Ranit Aharonov, Noam Slonim (AAAI 2020) Corpus wide argument mining - a working solution
  [bib] [pdf] [code] [Latex] 

• Leshem Choshen, Omri Abend (CoNLL 2019) Automatically Extracting Challenge Sets for Non-local Phenomena in Neural Machine Translation
  [bib] [pdf] [code] [Latex]

• Leshem Choshen, Dan Eldad, Daniel Hershcovich, Elior Sulem, Omri Abend (ACL 2019) The Language of Legal and Illegal Activity on the Darknet
  [bib] [pdf] [code] [Latex] 

• Martin Gleize, Eyal Shnarch, Leshem Choshen, Lena Dankin, Guy Moshkowich, Ranit Aharonov, Noam Slonim (ACL 2019) Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network
  [bib] [pdf] [code] [Latex] 

• Yoav Kantor, Yoav Katz, Leshem Choshen*, Edo Cohen-Karlik, Naftali Liberman, Assaf Toledo, Amir Menczel, Noam Slonim (BEA 2019) Learning to combine Grammatical Error Corrections
  [bib] [pdf] [code] [Latex] 

• Leshem Choshen & Omri Abend (ACL 2018) Inherent Biases in Reference-based Evaluation for Grammatical Error Correction and Text Simplification
  [bib] [pdf] [code] [Latex] 

• Leshem Choshen & Omri Abend (ACL 2018) Automatic Metric Validation for Grammatical Error Correction
  [bib] [pdf] [code] [Latex]

• Eyal Shnarch, Carlos Alzate, Lena Dankin, Martin Gleize, Yufang Hou, Leshem Choshen, Ranit Aharonov and Noam Slonim (ACL 2018) Will it Blend? Weak and Manual Labeled Data in a Neural Network for Argumentation Mining
  [bib] [pdf] [code] [Latex]

• Leshem Choshen, Lior Fox, Yonatan Loewenstein (ICLR 2018) DORA The Explorer: Directed Outreaching Reinforcement Action-Selection
  [bib] [pdf] [code] [Latex]

• Leshem Choshen & Omri Abend (NAACL-HLT 2018) Reference-less Measure of Faithfulness for Grammatical Error Correction
  [bib] [pdf] [code] [Latex]

Errata

​​

• Automatic Metric Validation for Grammatical Error Correction - Alignment is node alignment and not edge alignment. It is equivalent up to the top nodes of the DAG which should be aligned with each other.