Esin Durmus



Contact: ed459 AT cornell DOT edu

Hi! I am Esin Durmus. I am a PhD candidate in the Computer Science department at Cornell University advised by Claire Cardie. In Fall 2020, I am also a co-instructor of CS4740 (Introduction to NLP) at Cornell University.

UPDATE: I will be joining Stanford NLP group as a Postdoc towards the end of Spring 2021. I will be co-hosted by Dan Jurafsky, Tatsu Hashimoto and Chris Manning.

Research Interests

  • Natural Language Processing
  • Natural Language Generation
  • Interpretability & Evaluation
  • Argument Generation
  • Argumentation Mining
  • Computational Social Science
  • Social Media Analysis

I am interested in a broad set of problems in Natural Language Processing including faithfulness, interpretability, evaluation and bias of neural generation systems. I am also interested in social applications of NLP such as understanding characteristics of persuasive arguments and argument generation.


News

  • I will be joining Stanford NLP as a Postdoc in Spring 2021.
  • I am co-teaching an CS4740 with my advisor in Fall 2020.
  • I am interning at Google AI Research in Summer 2020.
  • Selected as one of the Rising Stars in EECS 2019 by UIUC.

Publications

  • WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization
    Faisal Ladhak, Esin Durmus , Claire Cardie and Kathleen McKeown.
    To apper in Findings of EMNLP, 2020.
    [paper] [data] [bib]

  • Exploring the Role of Argument Structure in Online Debate Persuasion
    Jialu Li, Esin Durmus and Claire Cardie.
    To appear in EMNLP, 2020.
    [paper] [bib]

  • A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization
    Esin Durmus, He He and Mona Diab.
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2020.
    [paper] [code]

  • The Role of Pragmatic and Discourse Context in Determining Argument Impact
    Esin Durmus, Faisal Ladhak and Claire Cardie.
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019.
    [paper] [bib]

  • Determining Relative Argument Specificity and Stance for Complex Argumentative Structures
    Esin Durmus, Faisal Ladhak and Claire Cardie.
    In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
    [paper] [bib]

  • A Corpus for Modeling User and Language Effects in Argumentation on Online Debating
    Esin Durmus and Claire Cardie.
    In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
    [paper] [bib] [dataset]

  • Persuasion of the Undecided: Language vs. the Listener
    Liane Longpre, Esin Durmus and Claire Cardie.
    In Proceedings of the 6th Workshop in Argumentation Mining 2019.
    [paper] [bib] [dataset]

  • Modeling the Factors of User Success in Online Debate
    Esin Durmus and Claire Cardie.
    In Proceedings of the World Wide Web Conference (WWW), 2019.
    [paper] [bib] [dataset]
    Cornell Chronicle Story

  • Exploring the Role of Prior Beliefs for Argument Persuasion
    Esin Durmus and Claire Cardie.
    In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2018.
    [paper] [bib] [dataset]

  • Understanding the Effect of Gender and Stance on Opinion Expression in Debates on "Abortion”.
    Esin Durmus and Claire Cardie.
    In Proceedings of PEOPLES2018 workshop (co-organized with NAACL) on computational modeling of peoples opinions, personality, and emotions in social media.
    [paper] [bib]

  • Cornell Belief and Sentiment System at TAC 2016
    Vlad Niculae, Kai Sun, Xilun Chen, Yao Cheng, Xinya Du, Esin Durmus, Arzoo Katiyar and Claire Cardie.
    Text Analysis Conference (TAC), 2016.
    [paper] [bib]

Datasets


Teaching

  • Instructor for Introduction to Natural Language Processing, Cornell University. Fall 2020.
  • Teaching Assistant for Introduction to Natural Language Processing, Cornell University. Fall 2016, Fall 2017, Fall 2019.
  • Teaching Assistant for Machine Learning for Data Science, Cornell University. Spring 2016.
  • Teaching Assistant for Introduction to Web Design, Cornell University. Fall 2015.

Research Mentorship Experience

I have had opportunity to mentor several Undergraduate and Master students in Cornell to help them develop skills in conducting NLP research.

Students

  • Xinran Zhao: Spring 2018 - Present.
  • Jialu Li: Fall 2018 - Fall 2020.
  • Liane Longpre: Fall 2018 - Summer 2019.

Industry Experience

  • Google AI Research. Summer 2020 - Present.
  • Applied Scientist Intern in Amazon AWS. Summer 2019 - December 2019.
  • Applied Scientist Intern in Amazon Alexa. Summer 2017.

Contact

You can contact me at ed459 AT cornell DOT edu.

Design: HTML5 UP.