Publications

You can find more information on my publications on my Google Scholar page.

Work in Progress

1. Brannon, W., Fulay, S., Jiang, H., Kang, W., Roy, B., Kabbara, J., & Roy, D. (2023). ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings. Retrieved from https://arxiv.org/abs/2305.14321
   
   @unpublished{brannon2023congrat,
     title = {{ConGraT}: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings},
     author = {Brannon, William and Fulay, Suyash and Jiang, Hang and Kang, Wonjune and Roy, Brandon and Kabbara, Jad and Roy, Deb},
     note = {arXiv preprint arXiv:2305.14321},
     url = {https://arxiv.org/abs/2305.14321},
     year = {2023}
   }
   

2. Longpre, S., Mahari, R., Chen, A., Obeng-Marnu, N., Sileo, D., Brannon, W., … others. (2023). The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI. Retrieved from https://arxiv.org/abs/2310.16787
   
   @unpublished{longpre2023dpi,
     title = {The {D}ata {P}rovenance {I}nitiative: A Large Scale Audit of Dataset Licensing \& Attribution in {AI}},
     author = {Longpre, Shayne and Mahari, Robert and Chen, Anthony and Obeng-Marnu, Naana and Sileo, Damien and Brannon, William and Muennighoff, Niklas and Khazam, Nathan and Kabbara, Jad and Perisetla, Kartik and others},
     note = {arXiv preprint arXiv:2310.16787},
     url = {https://arxiv.org/abs/2310.16787},
     year = {2023}
   }
   

Journal Articles

1. Brannon, W., Virkar, Y., & Thompson, B. (2023). Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing. Transactions of the Association for Computational Linguistics, 11, 419–435.
   
   @article{brannonDubbingInPractice2023,
     title = {Dubbing in {{Practice}}: {{A Large Scale Study}} of {{Human Localization With Insights}} for {{Automatic Dubbing}}},
     shorttitle = {Dubbing in {{Practice}}},
     author = {Brannon, William and Virkar, Yogesh and Thompson, Brian},
     year = {2023},
     journal = {Transactions of the Association for Computational Linguistics},
     volume = {11},
     pages = {419--435},
     issn = {2307-387X},
     doi = {10/gr9cbz},
     urldate = {2023-05-24},
     langid = {english}
   }
   

Conference Articles

1. Longpre, S., Mahari, R., Muennighoff, N., Chen, A., Perisetla, K., Brannon, W., … Hooker, S. (2023). The Data Provenance Project. Proceedings of the 40th International Conference on Machine Learning.
   
   @inproceedings{longpre2023data,
     title = {The {D}ata {P}rovenance {P}roject},
     author = {Longpre, Shayne and Mahari, Robert and Muennighoff, Niklas and Chen, Anthony and Perisetla, Kartik and Brannon, William and Kabbara, Jad and Villa, Luis and Hooker, Sara},
     booktitle = {Proceedings of the 40th International Conference on Machine Learning},
     booksubtitle = {{GenLaw} '23},
     year = {2023}
   }
   

2. Beeferman, D., Brannon, W., & Roy, D. (2019). RadioTalk: A Large-Scale Corpus of Talk Radio Transcripts. Interspeech 2019, 564–568. ISCA.
   
   @inproceedings{RadioTalk2019,
     title = {{{RadioTalk}}: {{A Large-Scale Corpus}} of {{Talk Radio Transcripts}}},
     booktitle = {Interspeech 2019},
     author = {Beeferman, Doug and Brannon, William and Roy, Deb},
     year = {2019},
     pages = {564--568},
     publisher = {{ISCA}},
     location = {{Graz, Austria}},
     doi = {10/gpcff2},
     urldate = {2019-09-23}
   }
   

Theses

1. Brannon, W. (2020). Mapping U.S. Talk Radio: A Textual Survey at Scale (M.S. Thesis, Massachusetts Institute of Technology). Massachusetts Institute of Technology.
   
   @mastersthesis{brannonMappingTalkRadio2020,
     author = {Brannon, William},
     title = {Mapping {{U}}.{{S}}. {{Talk Radio}}: {{A Textual Survey}} at {{Scale}}},
     school = {Massachusetts Institute of Technology},
     location = {{Cambridge, MA}},
     type = {M.S. Thesis},
     url = {https://hdl.handle.net/1721.1/129270},
     year = {2020},
     langid = {english},
     pagetotal = {140}
   }