EILEEN BLUM

ABOUT ME

I am a seventh year abd PhD student in the linguistics department at Rutgers University. I am interested mainly in computational phonology. My dissertation uses a formal language theory approach to investigate the computational complexity of vowel harmony patterns over multi-tiered autosegmental representations. I plan to complete my dissertation for a January 2022 graduation.

Outside of academia, I also enjoy training animals and medieval armored combat. I have ridden and trained off-the-track thoroughbreds in the hunter/jumper discipline for over ten years. I trained my first dog as a kid and now I am training my cat to perform some basic tasks on cue. I also participated in heavy combat in the Society for Creative Anachronism (SCA) and I enjoy larp and boffer fighting with an affinity for pole weapons, particularly glaive and axe.

EDUCATION

PHD LINGUISTICS, RUTGERS UNIVERSITY

September 2015 - January 2022

BA LINGUISTICS, UNIVERSITY OF CALIFORNIA SANTA CRUZ

September 2012 - June 2014

INTERSEGMENTAL GENERAL EDUCATION TRANSFER CURRICULUM, DIABLO VALLEY COLLEGE

August 2010 - May 2012

July 2021 - Present

DIALOGUE DESIGNER, TEK SYSTEMS

Google CCAI

• Label conversational data to monitor and improve Verizon voice/chat bots

• Implement NLU tuning improvements directly within automated agents

• Aid in development and testing of a new label taxonomy to increase consistency across the team

• Streamline tasks to create an easy repeatable process

September 2015 - June 2021

LINGUISTICS FELLOW & TA, RUTGERS UNIVERSITY

Research: Phonology, Formal Language Theory, Computational complexity, Acoustic experimentation

• Execute two major research projects over six years: design, structure, analysis, and maintained schedule from inception to completion

• Develop theory to explain how abstract representations affect the computational complexity of sound patterns across languages

• Record 20 native speakers to determine word stress pattern in Munster Irish

• Collaborate with experts in four disciplines: computer science, math, linguistics, and cognitive psychology

• Strong proficiency with IPA and excellent understanding of other phonological representations

• Teach two introduction to linguistics courses with 30 students each, Coordinate recitation section of 15 students for a course of 150

• Organize and host first PhD to Industry informational event with five panelists and up to 50 attendees

• Orchestrate summer mini-course with five lessons on methods of artificial learning

• Coordinate colloquium series for two years

PROJECTS

DISSERTATION

(tentative title): How locality of vowel harmony is affected by representations (Jan 2022)

I apply formal language theory to natural language data in order to analyze the computational complexity of vowel harmony patterns across both well studied and understudied languages. I use this computational approach to investigate the effects of different representational primitives on computation and develop a new theory of autosegmental locality.

METAL LYRICS GENERATOR

Erdös Institute Natural Language Processing Bootcamp, February-March, 2021

My partner and I built a Wasserstein Generative Adversarial Network (WGAN) in Python to generate automated song lyrics in lines of 8 words at a time. We compared our WGAN with a Soft-GAN. We trained both GANs on a Kaggle dataset of metal song lyrics, which we processed using NLTK and pandas. The GANs were built using Keras, Tensorflow, and Numpy. Lastly, we calculated BLEU scores for both models and determined that neither generated very natural sounding lyrics: WGAN received all 0s, Soft-GAN averaged 0.06 for n-grams of length 1-4.

METAL OR NOT?

Erdös Institute Data Science Bootcamp, May 2020

My partner and I created a classifier in Python to distinguish song lyrics by genre. We used two Kaggle data sets of song lyrics, which were cleaned using the GenSim and NLTK packages. We then used the shallow neural network in the Word2Vec package to create high-dimensional word vectors, PCA and k-clustering to group them based on semantic similarity, and trained a DecisionTreeClassifier to distinguish lyric sets. The classifier achieved 81% accuracy.

QUALIFYING PAPER 2

On the locality of vowel harmony over autosegmental representations (2018)

I applied Formal Language Theory to natural language data in order to analyze the computational complexity of vowel harmony patterns over autosegmental representations. I analyzed vowel harmony patterns in multiple languages and predicted possible cross-linguistic variation.

QUALIFYING PAPER 1

Allophony-driven stress in Munster Irish (2018)

I designed and implemented a production experiment to determine the word stress pattern of Munster Irish (Gaelic). I organized all the data files by hand in Excel, then annotated, transcribed, and analyzed all of the acoustic data by hand in Praat. Statistic analyses was performed using t-tests in Excel then verified using linear mixed effects models in R.

CONFERENCE PRESENTATIONS