Maryam Honari

maryamjhonari [at) g|\/|ail dot com

I’m a Machine Learning Engineer at Unity Technologies contributing to ML-agents toolkit. My focus is on leveraging Reinforcement and imitation learning to training intelligent agents, including providing a user-friendly package for state of the art methods and maintaining an open source project.

I received my Master’s degree degree under supervision of Dr. Alona Fyshe from Computer Science Department University of Victoria where I studied Natural language processing (NLP), machine learning and their applications to understand language composition in human brain.

news

Sep 15, 2021	If you’re attending GHC 2021 make sure to checkout our talk, “Enabling Cooperative Behaviors in Multiplayer Games Using Deep Reinforcement Learning”.
Mar 20, 2021	“Neural representation of words within phrases” is accepted in PLOS ONE.
Feb 1, 2021	I joined Unity technologies as a Machine Learning Engineer.

selected publications

PloS one

Neural representation of words within phrases: Temporal evolution of color-adjectives and object-nouns during simple composition

Honari-Jahromi, Maryam*, Chouinard, Brea*, Blanco-Elorrieta, Esti, Pylkkänen, Liina, and Fyshe, Alona

PloS one 2021

Abs HTML PDF Code

In language, stored semantic representations of lexical items combine into an infinitude of complex expressions. While the neuroscience of composition has begun to mature, we do not yet understand how the stored representations evolve and morph during composition. New decoding techniques allow us to crack open this very hard question: we can train a model to recognize a representation in one context or time-point and assess its accuracy in another. We combined the decoding approach with magnetoencephalography recorded during a picture naming task to investigate the temporal evolution of noun and adjective representations during speech planning. We tracked semantic representations as they combined into simple two-word phrases, using single words and two-word lists as non-combinatory controls. We found that nouns were generally more decodable than adjectives, suggesting that noun representations were stronger and/or more consistent across trials than those of adjectives. When training and testing across contexts and times, the representations of isolated nouns were recoverable when those nouns were embedded in phrases, but not so if they were embedded in lists. Adjective representations did not show a similar consistency across isolated and phrasal contexts. Noun representations in phrases also sustained over time in a way that was not observed for any other pairing of word class and context. These findings offer a new window into the temporal evolution and context sensitivity of word representations during composition, revealing a clear asymmetry between adjectives and nouns. The impact of phrasal contexts on the decodability of nouns may be due to the nouns’ status as head of phrase—an intriguing hypothesis for future research.
Thesis

Decoding semantic representations during production of minimal adjective-noun phrases

Honari-Jahromi, Maryam

2019

Abs HTML

Through linguistic abilities, our brain can comprehend and produce an infinite number of new sentences constructed from a finite set of words. Although recent research has uncovered the neural representation of semantics during comprehension of isolated words or adjective-noun phrases, the neural representation of the words during utterance planning is less understood. We apply existing machine learning methods to Magnetoencephalography (MEG) data recorded during a picture naming experiment, and predict the semantic properties of uttered words before they are said. We explore the representation of concepts over time, under controlled tasks, with varying compositional requirements. Our results imply that there is enough information in brain activity recorded by MEG to decode the semantic properties of the words during utterance planning. Also, we observe a gradual improvement in the semantic decoding of the first uttered word, as the participant is about to say it. Finally, we show that, compared to non-compositional tasks, planning to compose an adjective-noun phrase is associated with an enhanced and sustained representation of the noun. Our results on the neural mechanisms of basic compositional structures are a small step towards the theory of language in the brain.
EMNLP

Ensemble methods for native language identification

Chan, Sophia*, Honari-Jahromi, Maryam*, Benetti, Benjamin*, Lakhani, Aazim, and Fyshe, Alona

In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications 2017

Abs PDF Code

Our team—Uvic-NLP—explored and evaluated a variety of lexical features for Native Language Identification (NLI) within the framework of ensemble methods. Using a subset of the highestperforming features, we train Support Vector Machines (SVM) and Fully Connected Neural Networks (FCNN) as base classifiers, and test different methods for combining their outputs. Restricting our scope to the closed essay track in the NLI Shared Task 2017, we find that our best SVM ensemble achieves an F1 score of 0.8730 on the test set.