no code implementations • LREC 2022 • Chen Gafni, Anat Prior, Shuly Wintner
We present the Hebrew Essay Corpus: an annotated corpus of Hebrew language argumentative essays authored by prospective higher-education students.
no code implementations • LREC 2022 • Isabelle Nguyen, Shuly Wintner
We present classifiers that can accurately predict the proficiency level of nonnative Hebrew learners.
1 code implementation • 29 Aug 2023 • Shuly Wintner, Safaa Shehadi, Yuli Zeira, Doreen Osmelak, Yuval Nov
Why do bilingual speakers code-switch (mix their two languages)?
1 code implementation • ACL 2022 • Alissa Ostapenko, Shuly Wintner, Melinda Fricke, Yulia Tsvetkov
Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task.
no code implementations • ACL 2021 • Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner, Yulia Tsvetkov
State-of-the-art machine translation (MT) systems are typically trained to generate the "standard" target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language.
1 code implementation • IJCNLP 2019 • Sachin Kumar, Shuly Wintner, Noah A. Smith, Yulia Tsvetkov
Despite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well.
no code implementations • RANLP 2019 • Ilia Sominsky, Shuly Wintner
Parallel corpora are crucial resources for NLP applications, most notably for machine translation.
no code implementations • EMNLP 2018 • Gili Goldin, Ella Rabinovich, Shuly Wintner
We address the task of native language identification in the context of social media content, where authors are highly-fluent, advanced nonnative speakers (of English).
no code implementations • EMNLP 2018 • Anjalie Field, Doron Kliger, Shuly Wintner, Jennifer Pan, Dan Jurafsky, Yulia Tsvetkov
Amidst growing concern over media manipulation, NLP attention has focused on overt strategies like censorship and "fake news'".
1 code implementation • TACL 2018 • Ella Rabinovich, Yulia Tsvetkov, Shuly Wintner
We present a computational analysis of cognate effects on the spontaneous linguistic productions of advanced non-native speakers.
no code implementations • 20 May 2018 • Elad Tolochinsky, Ohad Mosafi, Ella Rabinovich, Shuly Wintner
This work distinguishes between translated and original text in the UN protocol corpus.
no code implementations • ACL 2017 • Ella Rabinovich, Noam Ordan, Shuly Wintner
Translation has played an important role in trade, law, commerce, politics, and literature for thousands of years.
no code implementations • COLING 2016 • Shuly Wintner
Translated texts, in any language, have unique characteristics that set them apart from texts originally written in the same language.
no code implementations • EACL 2017 • Ella Rabinovich, Shachar Mirkin, Raj Nath Patel, Lucia Specia, Shuly Wintner
The language that we produce reflects our personality, and various personal and demographic characteristics can be detected in natural language texts.
no code implementations • TACL 2015 • Ella Rabinovich, Shuly Wintner
We show that this is indeed the case, in a variety of evaluation scenarios.
no code implementations • ACL 2016 • Ella Rabinovich, Sergiu Nisioi, Noam Ordan, Shuly Wintner
We present a computational analysis of three language varieties: native, advanced non-native, and translation.
no code implementations • LREC 2016 • Sergiu Nisioi, Ella Rabinovich, Liviu P. Dinu, Shuly Wintner
We describe a monolingual English corpus of original and (human) translated texts, with an accurate annotation of speaker properties, including the original language of the utterances and the speaker{'}s country of origin.
no code implementations • 11 Sep 2015 • Ella Rabinovich, Shuly Wintner, Ofek Luis Lewinsohn
To validate the quality and reliability of the corpora, we replicated previous results of supervised and unsupervised identification of translationese, and further extended the experiments to additional datasets and languages.