About | Skills | Education | Service

My love for data science and language data, which forms the basis for so much of “AI”, comes from the joy of discovering patterns in how people use spoken and written language in context. In my academic work, I’ve sought explanations for why such patterns exist and how they might develop over time. In my professional career, I have combined my background in experimental design, statistics and linguistics to improve the performance of spoken language understanding models that underlie a virtual assistant (Alexa), as well as multilingual LLMs (LLaMa 3 & 4).

As a data scientist with Amazon Alexa, my work has directly led to a better understanding of user behaviour and improvements in customer experiences across 9 different languages when they use products like alarms, timers, reminders, notes and weather. As a linguistic engineer lead at Meta Applied LLaMa, I managed data collection across 30 languages (from creating taxonomies and annotation guidelines to monitoring quality assurance), and curated multi-turn datasets for training agents.

Sunrise over Zunheboto town in Nagaland, India

Back to top

---

SKILLS

MACHINE LEARNING ALGORITHMS

Linear regression & Logistic regression
Decision trees & Random forests
K-means & Hierarchical clustering

DATA VISUALIZATION

Python (matplotlib & seaborn)
R (ggplot2 and ggmap)
Tableau dashboards

LINGUISTIC & CULTURAL COMPETENCIES

English (native)
French (excellent speaking/listening/reading/writing)
Mandarin Chinese (excellent speaking/listening/reading/writing)
Russian (good reading/writing)

Countries lived and worked in: Canada, USA, Australia, Singapore, France, China.
Countries I’ve done fieldwork in: India, Nepal

Back to top

---

EDUCATION

UNIVERSITY OF OREGON

Ph.D. in Linguistics
(September 2013 – June 2019)
Dissertation: “Investigating differential case marking in Sumi, a language of Nagaland, using language documentation and experimental methods”

UNIVERSITY OF MELBOURNE

M.A. in Linguistics
(March 2008 – June 2010)
Thesis: “Sumi tone: A phonological and phonetic description of a Tibeto-Burman language of Nagaland”

B.A. (Honours)
Majors: Linguistics, Russian
Diploma of Modern Languages (French)
(March 2002 – December 2007)
Honours thesis: “Breaking up is hard to do: Teasing apart morphological complexity in Iwaidja and Maung”

Back to top

---

OUTREACH / SERVICE

Service

Glamazon: Vancouver Pride march co-captain (2022)

Alexa Home Productivity Diversity Equity and Inclusion committee member & advocate (2022-2023)

---

Public talks

“How to construct a language” at Foreign Languages and International Studies (FLIS) Day for high school students at University of Oregon . With Charlotte Vaughn. (4 May 2018; 3 May 2019)

“Vital Voices” fundraiser for GLOSS (Graduate Linguists of Oregon Student Society) (3 May 2018)

Back to top