Ganesh

Ph.D. student
University of British Columbia

Resume | Github | Google-Scholar | LinkedIn | Contact

I am interested in making machines understand natural language better.

arXiv Papers

1. Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts (arxiv, code)
   Ganesh J, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra
   
2. Orca: Progressive Learning from Complex Explanation Traces of GPT-4 (arxiv)
   Subhabrata Mukherjee, Arindam Mitra, Ganesh J, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah
   

Published Papers

1. AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers (arxiv, code)
   Ganesh J, Subhabrata Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah, Sebastien Bubeck, Jianfeng Gao
   Findings of the Association for Computational Linguistics (ACL), Jul 9 - Jul 14, Toronto, Canada, 2023
2. Contrastive Learning of Sociopragmatic Meaning in Social Media (arxiv, code)
   Chiyu Zhang, Muhammad Abdul-Mageed, Ganesh J
   Findings of the Association for Computational Linguistics (ACL), Jul 9 - Jul 14, Toronto, Canada, 2023
3. Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints (arxiv, code)
   Ganesh J, Subhabrata Mukherjee, Debadeepta Dey, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan, Caio Cesar Teodoro Mendes, Gustavo Henrique de Rosa, Shital Shah
   Fourth Workshop on Simple and Efficient Natural Language Processing at ACL , Jul 9 - Jul 14, Toronto, Canada, 2023
4. Automatic Detection of Entity-Manipulated Text using Factual Knowledge (pdf, slides, poster)
   Ganesh J, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan
   Association for Computational Linguistics (ACL), May 22 - May 27, Dublin, Ireland, 2022
5. Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing (pdf, slides)
   Ganesh J, El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan
   Workshop on Computational Approaches to Linguistic Code-Switching at NAACL, June 11, Online, 2021
6. Automatic Detection of Machine Generated Text: A Critical Survey (arxiv, resources)
   Ganesh J, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan
   International Conference on Computational Linguistics, Dec 8 - Dec 13, Barcelona, Spain, 2020
7. Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora (pdf, slides, code, bibtex, video, chat, poster)
   Hila Gonen, Ganesh J, Djamé Seddah, Yoav Goldberg
   Association for Computational Linguistics, Jul 5 - Jul 10, Seattle, USA, 2020
8. What does BERT learn about the structure of language? (pdf, slides, code, bibtex, video, poster)
   Ganesh J, Benoit Sagot, Djamé Seddah
   Association for Computational Linguistics, Jul 28 - Aug 2, Florence, Italy, 2019
9. Contextualized Diachronic Word Representations (pdf, slides, code, bibtex, video)
   Ganesh J, Djamé Seddah
   Workshop on Historical Language Change at Association for Computational Linguistics, Jul 28 - Aug 2, Florence, Italy, 2019
10. ELMoLex: Connecting ELMo and Lexicon features for Dependency Parsing (pdf, code, poster, bibtex)
    Ganesh J, Benjamin Muller, Amal Fethi, Louis Martin, Eric de La Clergerie, Benoit Sagot, Djamé Seddah
    CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Oct 31 - Nov 4, Brussels, Belgium, 2018
11. Towards Interpretation of Node Embeddings (pdf, poster, bibtex, code)
    Ayushi Dalmia, Ganesh J, Manish Gupta
    International Workshop on Learning Representations for Big Networks at The Web Conference, Apr 24, Lyon, France, 2018
12. Improving Distributed Representations of Tweets - Present and Future (pdf, poster, bibtex)
    Ganesh J
    ACL Student Research Workshop (SRW), Jul 30 - Aug 4, Vancouver, Canada, 2017
13. Discovery and Interpretation of Embedding Models for Knowledge Representation (Master's Thesis) (pdf, slides)
    Ganesh J
    International Institute of Information Technology Hyderabad (IIITH), Jun 17, Hyderabad, India, 2017
14. Interpretation of Semantic Tweet Representations (arxiv, pdf, bibtex, code, slides)
    Ganesh J, Manish Gupta, Vasudeva Varma
    The 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Jul 31 - Aug 3, Sydney, Australia, 2017
15. Multi-part Representation Learning For Cross-domain Web Content Classification using Neural Networks (pdf, slides, bibtex)
    Ganesh J, Himanshu Sharad Bhatt, Manjira Sinha, Shourya Roy
    The 28th ACM Conference on Hypertext and Social Media (HT), Jul 4-7, Prague, Czech Republic, 2017
16. Improving Tweet Representations using Temporal and User Context (arxiv, pdf, slides, poster, bibtex, code)
    Ganesh J, Manish Gupta, Vasudeva Varma
    The 39th European Conf. on Information Retrieval (ECIR), Apr 9-13, Aberdeen, Scotland UK, 2017
17. Interpreting the Syntactic and Social Elements of the Tweet Representations via Elementary Property Prediction Tasks (arxiv, pdf, slides, poster, bibtex, code)
    Ganesh J, Manish Gupta, Vasudeva Varma
    NIPS Workshop on Interpretable Machine Learning in Complex Systems, Dec 9, Barcelona, Spain, 2016
18. Doc2Sent2Vec: A Novel Two-Phase Approach for Learning Document Representation (pdf, slides, poster, bibtex, code)
    Ganesh J, Manish Gupta, Vasudeva Varma
    The 39th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), Jul 17-21, Pisa, Italy, 2016
19. Author2Vec: Learning Author Representations by Combining Content and Link Information (pdf, slides, poster, bibtex, code)
    Ganesh J, Soumyajit Ganguly, Manish Gupta, Vasudeva Varma, Vikram Pudi
    The 25th International World Wide Web Conference (WWW), Apr 11-25, Montreal, Canada, 2016