| |
|
|
| |
EVENT DETAILS |
"Importance of Data & Controllability in Neural Language Generation"
About this event
Natural language generation has become a popular playground for deep learning techniques. In this talk, I will demonstrate that creating high-quality training data & introducing controllability over different editing operations (such as paraphrasing, sentence splitting, etc.) can lead to significant performance improvements that overshadow gains from model variations. In particular, I will focus on the text simplification task that improves text accessibility, including: (1) a monolingual word alignment model that can identify semantically related text spans between two sentences for analyzing human editing operations; (2) a controllable text generation approach that incorporates syntax through pairwise ranking & data argumentation; (3) a neural conditional random field (CRF) based semantic model to create parallel training data. I will also briefly discuss our other work on large-scale paraphrase acquisition from Twitter.
BIO
Wei Xu is an assistant professor in the School of Interactive Computing at the Georgia Institute of Technology. Xu received her Ph.D. in Computer Science from New York University, B.S. & M.S. from Tsinghua University. Her research interests are in natural language processing, machine learning, & social media. Her recent work focuses on text generation, semantics, information extraction, & reading assistive technology. She is a recipient of the NSF CAREER Award, CrowdFlower AI for Everyone Award, Criteo Faculty Research Award, & COLING Best Paper Award. She has also received funds from DARPA & IARPA, & is part of the new NSF AI CARING Institute.
|
|
|
|
|
|
