Ziang Xie

Hi 👋

Hi — I'm CEO of Sapling.ai, where we're working on a language model toolkit for enterprise applications. Work with us.

Previously, I did research in machine learning and natural language processing (see below).

Outside of work, you can find me getting pulled along by the little homie Deebo, at a bookstore, or running.

Writing

Personal

Please see my Substack (in development).

AI / Startups

You'll be able to find most of my essays on The Transducer.

Samples:

• 2024-07-07: The Last Mile
• 2023-10-18: ChatGPT's Favorite Phrases
• 2020-07-02: The Case for Human-in-the-Loop AI for Customer Conversations

Papers

• Neural Text Generation: A Practical Guide. arXiv:1711.09534, 2017 [pdf]
• Data Noising as Smoothing in Neural Network Language Models. Ziang Xie, Sida I. Wang, Jiwei Li, Daniel Levy, Aiming Nie, Dan Jurafsky, Andrew Y. Ng. ICLR, 2017 + Baylearn, 2016. [pdf] [code]
• Neural Language Correction with Character-Based Attention. Ziang Xie, Anand Avati, Naveen Arivazhagan, Dan Jurafsky, Andrew Y. Ng. arXiv:1603.09727, 2016 [pdf] [code]
• Lexicon-Free Conversational Speech Recognition with Neural Networks. Andrew L. Maas*, Ziang Xie*, Dan Jurafsky, Andrew Y. Ng. NAACL, 2015 [pdf]
• Building DNN Acoustic Models for Large Vocabulary Speech Recognition. Andrew L. Maas, Peng Qi, Ziang Xie, Awni Y. Hannun, Christopher T. Lengerich, Daniel Jurafsky, Andrew Y. Ng. Computer Speech & Language, Volume 41. [pdf]

Full listing: Google Scholar

Teaching

• Co-head TA, CS229, Machine Learning, Fall 2017
• Head TA, CS124, From Languages to Information, Spring 2017
• TA, CS229, Machine Learning, Fall 2016

Before

• PhD student, Computer Science, 2013—2018; Advisors: Andrew Ng, Dan Jurafsky; Thesis: Noising and Denoising Natural Language
• Intern, Summer 2016, Google Brain; Host: Quoc Le
• Undergraduate Researcher, 2011-2013, UC Berkeley (BAIR); Advisor: Pieter Abbeel

Other

• NDSEG Fellowship, 2014-2017
• Stanford SoE Fellowship, 2013-2014