Content Anchoring In Multimodal Texts: A Peek into the Prequel

◾ Content Anchoring In Multimodal Texts: A Peek into the Prequel

◾ Speaker: Khyathi Chandu

◾ Talk Description
This talk is part of the #wome_in_nlp talk series which invites women who successfully carved their career path in NLP to share their experiences and advice. Everyone is welcome to attend the talk not only women.

◾ Abstract
This talk takes you on a little trip to the life, choices, and routine challenges a Ph.D. student walks through. My biggest takeaway: patience is truly the most reliable compass to navigate this path. It emphasizes the importance of playing the long game by taking one step at a time.

This gradually leads to a part of contextualizing my research on the controllability of content in multimodal text generation. I will begin with denoising large image captioning models for single sentence generation and then discuss infilling techniques for visual procedure telling. I will conclude with some future directions on making NLP systems more grounded in everyday life.

◾ Learn more about Khyathi:
Khyathi Chandu is a fifth-year Ph.D. student in Language Technologies Institute at Carnegie Mellon University, advised by Professors Alan Black and Eric Nyberg. She also closely works with Prof Yonatan Bisk. The avid goal of her research is to enable seamless communication between humans and machines with multiple modalities and languages. Her current research focuses on multimodality and vision-and-language generation. She envisions a trajectory of her research towards virtual agents with augmented and virtual reality characters that appropriately interact with us. She has also done an array of work in code-switching, biomedical text summarization. In the past, she has experience working with some amazing hosts at Apple, Google AI, and the University of Pennsylvania during her past internships and is going to do an internship at Facebook AI this summer. She is awarded Rising Stars EECS 2020, won the sixth edition of the BioAsq challenge, has consistently been on Dean’s Merit list, and was awarded the Best All-Rounder Student in her undergraduate. She actively volunteers in several diversity efforts, organized workshops for Widening NLP in 2020 and 2021, and is co-chairing Academic Inclusion in ACL 2020 and 2021. She is also an editor for the Machine Learning Blog at CMU.

http://www.cs.cmu.edu/~kchandu/

◾ About #women_in_nlp
Website: https://efatmae.github.io/women_in_nlp
Twitter: https://twitter.com/fatmaElsafoury
Slack channel on dair.ai: https://dairai.slack.com/archives/C01J0GXJMD1

◾ About dair.ai
Website: https://dair.ai/
GitHub: https://github.com/dair-ai
Twitter: https://twitter.com/dair_ai
Newsletter: https://dair.ai/newsletter/
Slack: https://join.slack.com/t/dairai/shared_invite/zt-pcxkmoip-b4nJkci8L_dynpMwLvlCcQ

◾ Code of Conduct: https://github.com/dair-ai/dair-ai.github.io/blob/master/CODE_OF_CONDUCT.md