Minnesota Natural Language Processing Seminar Series: Reliable and Factual Natural Language Generation
The Minnesota Natural Language Processing (NLP) Seminar is a venue for faculty, postdocs, students, and anyone else interested in theoretical, computational, and human-centric aspects of natural language processing to exchange ideas and foster collaboration. The talks are every other Friday from 12 p.m. - 1 p.m. during the Spring 2022 semester.
This week's speaker, He He (NYU), will be giving a talk titled "Reliable and Factual Natural Language Generation"
Recent advances in large-scale neural language models have transformed the field of text generation, including applications like dialogue and document summarization. Despite human-like fluency, the generated text tends to contain incorrect, inconsistent, or hallucinated information, which hinders the deployment of text generation models in real applications. I will review observations of such errors in current generation tasks, explain challenges in evaluating and mitigating factual errors, and describe our recent attempts on addressing these problems. I will conclude with a discussion on future challenges and directions.
He He is an assistant professor at the Center for Data Science and the Department of Computer Science at New York University. Before joining NYU, she spent a year at Amazon Web Services and was a postdoc at Stanford University. She received her PhD from University of Maryland, College Park. She is interested in building trustworthy NLP systems in human-centered applications. Her current research focuses on text generation, dialogue systems, and robust language understanding.