publications

total: 26

2025

  1. Publication thumbnail Preprint
    An Interdisciplinary Approach to Human-Centered Machine Translation
    Marine Carpuat , Omri Asscher , Kalika Bali , Luisa Bentivogli , Frédéric Blain , Lynne Bowker , Monojit Choudhury , Hal Daumé III , Kevin Duh , Ge Gao , Alvin Grissom II , Marzena Karpinska , Elaine C. Khoong , William D. Lewis , André F. T. Martins , Mary Nurminen , Douglas W. Oard , Maja Popovic , Michel Simard , and François Yvon (2025)
    Paper
  2. Publication thumbnail Preprint
    OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
    Alisha Srivastava* , Emir Korukluoglu* , Minh Nhat Le* , Duyen Tran , Chau Minh Pham , Marzena Karpinska , and Mohit Iyyer (2025)
    Paper GitHub
  3. Publication thumbnail Preprint
    Does quantization affect models’ performance on long-context tasks?
    Anmol Mekala* , Anirudh Atmakuru* , Yixiao Song , Marzena Karpinska , and Mohit Iyyer (2025)
    Paper GitHub
  4. Publication thumbnail COLM
    One ruler to measure them all: Benchmarking multilingual long-context language models
    Yekyung Kim , Jenna Russell , Marzena Karpinska , and Mohit Iyyer (2025)
    Paper GitHub
  5. Publication thumbnail ACL
    People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
    Jenna Russell , Marzena Karpinska , and Mohit Iyyer (2025)
    Paper GitHub
  6. Publication thumbnail Preprint
    OverThink: Slowdown Attacks on Reasoning LLMs
    Abhinav Kumar , Jaechul Roh , Ali Naseh , Marzena Karpinska , Mohit Iyyer , Amir Houmansadr , and Eugene Bagdasarian (2025)
    Paper

2024

  1. Publication thumbnail COLM
    FABLES: Evaluating faithfulness and content selection in book-length summarization
    Yekyung Kim , Yapei Chang , Marzena Karpinska , Aparna Garimella , Varun Manjunatha , Kyle Lo , Tanya Goyal , and Mohit Iyyer
    First Conference on Language Modeling
    (2024)
    Paper GitHub
  2. Publication thumbnail EMNLP
    One Thousand and One Pairs: A "novel" challenge for long-context language models
    Marzena Karpinska , Katherine Thai , Kyle Lo , Tanya Goyal , and Mohit Iyyer
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
    (2024)
    Paper GitHub Website
  3. Publication thumbnail ACL
    CaLMQA: Exploring culturally specific long-form question answering across 23 languages
    Shane Arora* , Marzena Karpinska* , Hung-Ting Chen , Ipsita Bhattacharjee , Mohit Iyyer , and Eunsol Choi (2024)
    *equal contributions
    Paper GitHub
  4. Publication thumbnail WMT
    Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation
    Tom Kocmi , Vilém Zouhar , Eleftherios Avramidis , Roman Grundkiewicz , Marzena Karpinska , Maja Popović , Mrinmaya Sachan , and Mariya Shmatova
    Proceedings of the Ninth Conference on Machine Translation
    (2024)
    Paper
  5. Publication thumbnail COLING
    Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
    Taishi Nakamura , Mayank Mishra , Simone Tedeschi , Yekun Chai , Jason T Stillerman ,  ... , and Sampo Pyysalo
    The 31st International Conference on Computational Linguistics
    (2024)
    Paper
  6. Publication thumbnail LREC-COLING
    NarrativeTime: Dense Temporal Annotation on a Timeline
    Anna Rogers , Marzena Karpinska , Ankita Gupta , Vladislav Lialin , Gregory Smelkov , and Anna Rumshisky
    The 2024 Joint International Conference on Computational Linguistics, Language, Resources and Evaluation
    (2024)
    Paper GitHub

2023

  1. Publication thumbnail NeurIPS
    Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
    Kalpesh Krishna , Yixiao Song , Marzena Karpinska , John Wieting , and Mohit Iyyer
    Proceedings of the Thirty-seventh Annual Conference on Neural Information Processing Systems
    (2023)
    Paper GitHub
  2. Publication thumbnail WMT
    Large language models effectively leverage document-level context for literary translation, but critical errors persist
    Marzena Karpinska  and Mohit Iyyer
    Proceedings of the Eighth Conference on Machine Translation
    (2023)
    Paper
  3. Publication thumbnail ACL: Report
    Program Chairs’ Report on Peer Review at ACL 2023
    Anna Rogers , Marzena Karpinska , Jordan Boyd-Graber , and Naoaki Okazaki
    Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
    (2023)
    Paper

2022

  1. Publication thumbnail COLING
    Revisiting Statistical Laws of Semantic Shift in Romance Cognates
    Yoshifumi Kawasaki , Maëlys Salingre , Marzena Karpinska , Hiroya Takamura , and Ryo Nagata
    Proceedings of the 29th International Conference on Computational Linguistics
    (2022)
    Paper
  2. Publication thumbnail ANLP
    分散表現を用いたロマンス語同源語動詞の意味変化の分析 (Analysis of Semantic Shift in Romance Cognate Verbs Using Word Embeddings)
    Yoshifumi Kawasaki , Maëlys Salingre , Marzena Karpinska , Hiroya Takamura , and Ryo Nagata
    Proceedings of the 28th Annual Conference of the Association for Natural Language Processing
    (2022)
    Paper Award
  3. Publication thumbnail EMNLP
    Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
    Katherine Thai* , Marzena Karpinska* , Kalpesh Krishna , William Ray , Moira Inghilleri , John Wieting , and Mohit Iyyer
    Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
    (2022)
    *equal contributions
    Paper GitHub
  4. Publication thumbnail EMNLP
    ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
    Ankita Gupta , Marzena Karpinska , Wenlong Zhao , Kalpesh Krishna , Jack Merullo , Luke Yeh , Mohit Iyyer , and Brendan O’Connor
    Findings of the Association for Computational Linguistics: EACL 2023
    (2022)
    Paper GitHub
  5. Publication thumbnail EMNLP
    DEMETR: Diagnosing Evaluation Metrics for Translation
    Marzena Karpinska , Nishant Raj , Katherine Thai , Yixiao Song , Ankita Gupta , and Mohit Iyyer
    Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
    (2022)
    Paper GitHub

2021

  1. Publication thumbnail EMNLP
    The perils of using Mechanical Turk to evaluate open-ended text generation
    Marzena Karpinska , Nader Akoury , and Mohit Iyyer
    Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
    (2021)
    Paper

2019

  1. Publication thumbnail ICPhS
    How accented do Caucasian-looking vs. Asian-looking native speakers sound to a Japanese listener?
    Marzena Karpinska
    Proceedings of the The International Congress of Phonetic Sciences
    (2019)
    Paper
  2. Publication thumbnail Routledge
    Emoticons: Digital Lingua Franca or a Culture-Specific Product Leading to Misunderstandings?
    Marzena Karpinska , Paula Kurzawska , and Katarzyna Rozanska
    Emoticons, Kaomoji, and Emoji: The Transformation of Communication in the Digital Age (Routledge Research in Language and Communication)
    (2019)
    Paper
  3. Publication thumbnail KJEE
    The Discourse of Kyōyō and English Education in Japan
    Kimie Yamamura , Ryo Gakutani , Marzena Karpinska , Tetsuro Tanojiri , and Tom Gally
    Komaba Journal of English Education
    (2019)
    Paper

2018

  1. Publication thumbnail RelNLP
    Subcharacter Information in Japanese Embeddings: When Is It Worth It?
    Marzena Karpinska , Bofang Li , Anna Rogers , and Aleksandr Drozd
    Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP
    (2018)
    Paper Website

2015

  1. Publication thumbnail ICPhS
    Vowel perception by listeners from different English dialects
    Marzena Karpinska , Shodai Uchida , and Izabelle Grenon
    Proceedings of the The International Congress of Phonetic Sciences
    (2015)
    Paper