T.J. Trimble
Linguist - Facebook
2019-05-27 – Present
Linguist - PRO Unlimited @ Facebook
2018-01-08 – 2019-05-26
Linguist - Appen @ Facebook
2017-07-17 – 2018-01-07
  • Linguistics: Developed linguistic foundation and future for Hey Facebook on Facebook Portal, Oculus, and Ray-Ban Stories, shipping three open source data sets (TOP, TOPv2, and MTOP)
    • Worked with many partners to develop the schema, ontology, and guidelines for tree-based semantic parsing (TOP) from inception through product delivery, enabling the launch of Hey Facebook.
    • Managed a $10 million annual budget delivering quality data for several high impact domains including social, calling, messaging, and reminders across the entire stack, from ASR and NLU to NLG.
  • Software Engineering: Organized tools, processes, and workflows for ontology development, guidelines management, data quality, annotator training, inter-annotator agreement and model metrics, and annotation visualization, supporting the refresh of wit.ai
    • Designed and implemented annotation tools for collection and annotation tasks for NLP in React and Hack used to collect millions of annotations by hundreds of annotators across dozens of projects.
    • Worked with highly cross-functional team to implement a zero-to-one voice app management system with complex UX design, storage budget, and system design constraints.
  • Leadership: Acted as linguistic project lead for major organization initiatives, managed three direct reports and a project team of seven, and mentored interns, organizing projects and workloads, handling cross functional communication, and providing direction and mentorship.
    • Worked with Product Managers, Engineering Managers, and Technology Leads from across the product pipeline (ASR, NLU, Q&A, NLG, etc.) to create project goals, prepare technical plans, and execute.
    • Developed individuals' technical, soft, and mentoring skills through project leadership, goal setting, and mentoring.
  • Recruiting: Created and developed hiring goals, job postings, core competencies, and interview questions.
    • Conducted and reviewed dozens of interviews, acting as contractor hiring program coordinator.
    • Developed technical and non-technical roles in collaboration with key stakeholders and peers.
FirstRain, Inc.
Natural Language Processing Engineer
2015-04-06 — 2016-10-07
  • Information Extraction: Owned and improved an Information Extraction engine processing thousands of documents every day, built on top of Stanford’s TokensRegex system.
  • Entity Linking: Designed, developed, and deployed a system matching named entities with topics over 100,000 documents per day.
University of Washington 2012-09-24 — 2014-12-05
Master of Science - Computational Linguistics
  • Thesis: Extended the Grammar Matrix, an open source grammar engineering project using HPSG, to enable the morphological, syntactic, and semantic analysis of adjectives cross-linguistically.
  • Natural Language Processing: tokenization, POS tagging, chunking, parsing, word sense disambiguation, sentiment analysis, coreference resolution, etc. using FSA/FSTs, CKY, etc.
  • Machine Learning: classification, clustering, and sequence labeling using Neural Networks (DNN, CNN, RNN, etc.), Naïve Bayes, MaxEnt/Logistic Regression, K-means, etc.
Natural languages:
  • English (native)
  • French (intermediate)
  • Japanese (beginner)
  • Italian (beginner)
Programming languages:
  • Python (9 years)
  • JavaScript/React (9 years)
  • PHP/Hack (10 years)
  • Java (7 years)
NLP Packages (9 years):
  • nltk
  • coreNLP
  • spaCy
NLP/ML Software Packages (5 years):
  • TensorFlow
  • NumPy
VCS (10 years):
  • git
  • svn
  • mercurial
IDE (9 years):
  • Atom/VSCode/Nuclide
  • Eclipse