Sopan Khosla

I am a second year Masters student in the Language Technologies Institute at Carnegie Mellon University, Pittsburgh, where I am advised by Prof. Carolyn Rose. I am interested in coreference resolution, discourse modeling, information extraction from conversations, and external knowledge incorporation. My CV.

I did my Bachelors in Computer Science and Engineering from IIT Roorkee.

News

Jun 6, 2021 Presenting our work ‘Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance’ at NAACL 2021.
Nov 20, 2020 Announcing the CODI 2021 shared-task on coreference resolution in dialog.
Nov 20, 2020 Presenting our work ‘Using type information for entity coreference resolution’ at CODI@EMNLP.
Nov 16, 2020 Attending EMNLP 2020 and presenting our paper MedFilter.

Selected Publications

  1. ACL21
    Generating SOAP Notes from Doctor-Patient Conversations
    Kundan Krishna, Sopan Khosla, Jeffrey P Bigham, and Zachary C Lipton
    arXiv preprint arXiv:2005.01795 2021
  2. ACL21
    Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer
    Sharmila Nangi, Niyati Chhaya, Sopan Khosla, Nikhil Kaushik, and Harshit Nyati
    ACL 2021
  3. NAACL21
    Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance
    Sopan Khosla, James Fiacco, and Carolyn Rosé
    In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2021
  4. EMNLP20
    Improving Detection and Categorization of Task-relevant Utterances through Integration of Discourse Structure and Ontological Knowledge.
    Sopan Khosla, Shikhar Vashishth, Jill Lehman, and Carolyn Rose
    In The 2020 Conference on Empirical Methods in Natural Language Processing 2020
  5. CODI@EMNLP20
    Using Type Information to Improve Entity Coreference Resolution
    Sopan Khosla, and Carolyn Rose
    In Proceedings of the First Workshop on Computational Approaches to Discourse 2020
  6. ArXiv20
    LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification
    Sopan Khosla, Rishabh Joshi, Ritam Dutt, Alan W Black, and Yulia Tsvetkov
    arXiv preprint arXiv:2008.04820 2020
  7. SocInfo19
    Do Events Change Opinions on Social Media? Studying the 2016 US Presidential Debates
    Sopan Khosla, Niyati Chhaya, Shivam Jindal, Oindrila Saha, and Milind Srivastava
    In International Conference on Social Informatics 2019
  8. AAAI19
    Surveys without Questions: A Reinforcement Learning Approach
    Atanu R Sinha, Deepali Jain, Nikhil Sheoran, Sopan Khosla, and Reshmi Sasidharan
    In Proceedings of the AAAI Conference on Artificial Intelligence 2019
  9. PAKDD19
    Gated Convolutional Encoder-Decoder for Semi-supervised Affect Prediction
    Kushal Chawla, Sopan Khosla, and Niyati Chhaya
    In Pacific-Asia Conference on Knowledge Discovery and Data Mining 2019
  10. COLING18
    Aff2Vec: Affect–Enriched Distributional Word Representations
    Sopan Khosla, Niyati Chhaya, and Kushal Chawla
    In Proceedings of the 27th International Conference on Computational Linguistics 2018
  11. SocialNLP18
    Emotionx-ar: CNN-DCNN autoencoder based emotion classifier
    Sopan Khosla
    In Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media 2018