Home > Events > CLIP Colloquium: Alexander Rush (Harvard)

CLIP Colloquium: Alexander Rush (Harvard)

Time: 
Wednesday, April 25, 2018 - 11:00 AM to 12:00 PM
Location: 
3258 A.V. Williams Building (AVW)

Title: Challenges in End-to-End Generation

Abstract: Progress in NMT has led to optimism for text generation tasks such as summarization and dialogue, but it has been more difficult to quantify the successes and challenges in this space. In this talk, I will survey some of the recent advances in neural NLG, and present a successful implementation of these techniques for the 2017 E2E NLG challenge (Gehrmann et al, 2018). Despite success on these small scale examples, though, we see that similar models fail to scale to a more realistic data-to-document corpus. Analysis shows systems will need further improvements in discourse modeling, reference, and referring expression generation (Wiseman et al, 2017). Finally, I will end by presenting recent work in unsupervised NLG that shows promising results in neural style transfer using a continuous GAN-based text autoencoder (Zhao et al 2017). 

Bio: Alexander Rush is an Assistant Professor at the Harvard School of Engineering and Applied Sciences. His research group studies and develops systems for natural language processing with the goal of textual understanding. I am particularly interested in efficient algorithms for inference and learning, and systems that can utilize large textual corpora, e.g. the web. Hiswork utilizes methods from machine learning, deep learning, and combinatorial optimization, and targets applications such as syntactic parsing, coreference resolution, machine translation, and information extraction.