Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them H Gonen, Y Goldberg arXiv preprint arXiv:1903.03862, 2019 | 668 | 2019 |
Null it out: Guarding protected attributes by iterative nullspace projection S Ravfogel, Y Elazar, H Gonen, M Twiton, Y Goldberg arXiv preprint arXiv:2004.07667, 2020 | 321 | 2020 |
It's all in the name: Mitigating gender bias with name-based counterfactual data substitution RH Maudslay, H Gonen, R Cotterell, S Teufel arXiv preprint arXiv:1909.00871, 2019 | 145 | 2019 |
Demystifying prompts in language models via perplexity estimation H Gonen, S Iyer, T Blevins, NA Smith, L Zettlemoyer arXiv preprint arXiv:2212.04037, 2022 | 102 | 2022 |
Simple, interpretable and stable method for detecting words with usage change across corpora H Gonen, G Jawahar, D Seddah, Y Goldberg arXiv preprint arXiv:2112.14330, 2021 | 87 | 2021 |
It's not Greek to mBERT: inducing word-level translations from multilingual BERT H Gonen, S Ravfogel, Y Elazar, Y Goldberg arXiv preprint arXiv:2010.08275, 2020 | 44 | 2020 |
Automatically identifying gender issues in machine translation using perturbations H Gonen, K Webster arXiv preprint arXiv:2004.14065, 2020 | 39 | 2020 |
Xlm-v: Overcoming the vocabulary bottleneck in multilingual masked language models D Liang, H Gonen, Y Mao, R Hou, N Goyal, M Ghazvininejad, ... arXiv preprint arXiv:2301.10472, 2023 | 36 | 2023 |
How does grammatical gender affect noun representations in gender-marking languages? H Gonen, Y Kementchedjhieva, Y Goldberg arXiv preprint arXiv:1910.14161, 2019 | 30 | 2019 |
Language modeling for code-switching: Evaluation, integration of monolingual data, and discriminative training H Gonen, Y Goldberg arXiv preprint arXiv:1810.11895, 2018 | 30 | 2018 |
Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too? W Shi, X Han, H Gonen, A Holtzman, Y Tsvetkov, L Zettlemoyer arXiv preprint arXiv:2212.10539, 2022 | 27 | 2022 |
Dictionary-based phrase-level prompting of large language models for machine translation M Ghazvininejad, H Gonen, L Zettlemoyer arXiv preprint arXiv:2302.07856, 2023 | 26 | 2023 |
Identifying helpful sentences in product reviews I Gamzu, H Gonen, G Kutiel, R Levy, E Agichtein arXiv preprint arXiv:2104.09792, 2021 | 26 | 2021 |
Do all languages cost the same? tokenization in the era of commercial language models O Ahia, S Kumar, H Gonen, J Kasai, DR Mortensen, NA Smith, Y Tsvetkov arXiv preprint arXiv:2305.13707, 2023 | 23 | 2023 |
Analyzing the mono-and cross-lingual pretraining dynamics of multilingual language models T Blevins, H Gonen, L Zettlemoyer arXiv preprint arXiv:2205.11758, 2022 | 19 | 2022 |
Prompting language models for linguistic structure T Blevins, H Gonen, L Zettlemoyer arXiv preprint arXiv:2211.07830, 2022 | 18 | 2022 |
Semi supervised preposition-sense disambiguation using multilingual data H Gonen, Y Goldberg arXiv preprint arXiv:1611.08813, 2016 | 18 | 2016 |
Analyzing gender representation in multilingual models H Gonen, S Ravfogel, Y Goldberg arXiv preprint arXiv:2204.09168, 2022 | 13 | 2022 |
Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. arXiv 2019 H Gonen, Y Goldberg arXiv preprint arXiv:1903.03862, 2019 | 10 | 2019 |
Pick a fight or bite your tongue: Investigation of gender differences in idiomatic language usage E Rabinovich, H Gonen, S Stevenson arXiv preprint arXiv:2011.00335, 2020 | 6 | 2020 |