Event Details

Traditional Natural Language Generation (NLG) methods incorporated a planning stage where the content of the text to be generated was planned before its surface realization. However, with the advent of sequence-2-sequence models, modern NLG methods have gravitated towards directly generating text from the input without an explicit planning stage. This compromises the narrative flow and quality of the text and makes the generation process difficult to steer.

In this talk, I discuss our approaches to text generation that incorporate content-plans. In the first part of the talk, I describe our approach to the problem of data-2-text generation. A key challenge in this problem is the structural gap between the input graph and the output (sequential) text. We bridge this structural gap by inserting an automatically generated content-plan between the input and the output. In the second part of the talk, I show how this idea can be extended to multi-document summarization. We show that a simple approach to plan the order in which the input documents are presented to the summarization model can boost the performance even outperforming models with complex architectures. In the last part of the talk, I describe our approach to incorporating a user-provided plan for the task of story generation. We use Reinforcement Learning to encourage the generation model to adhere to the plan and show that our approach results in text that fits the user’s plan while maintaining its coherence.

Speaker Bio

Snigdha Chaturvedi is an Assistant Professor of Computer Science at the University of North Carolina, Chapel Hill. She specializes in Natural Language Processing with an emphasis on narrative-like and socially aware understanding, summarization, and generation of language. Previously, she was an Assistant Professor at UC-Santa Cruz, and a postdoctoral fellow at UIUC and UPenn working with Dan Roth. She earned her Ph.D. in Computer Science from UMD in 2016, where she was advised by Hal Daume III.

YOU ONLY NEED TO REGISTER ONCE TO ATTEND THE ENTIRE SERIES – We will send you email announcements with details of the upcoming speakers.

Register in advance for this webinar: https://usc.zoom.us/webinar/register/WN__0VhakI6Q6i3JsasdmNWcA

After registering, you will receive an email confirmation containing information about joining the Zoom webinar.

The recording for this AI Seminar talk will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI.

Host: Muhao Chen, POC: Alma Nava