Experience

Graphic

Microsoft Research AI Software Engineer

As a Microsoft Research AI Resident, developed a state-of-the-art deep neural-net conversational agent model in Pytorch. The code and final draft are now publicly available. I also co-authored TwoPaneView for React Native which enables the dynamic rendering of Views on dual screen devices like the Microsoft Surface Duo.

Sept. 2019 - present

Graphic

Solvvy Software Engineering Intern

As a software engineering intern at Solvvy, developed and trained large deep neural network models on hundreds of thousands of GCloud Kubernetes-managed, PostgreSQL-stored ticket queries to classify and draw insights from text data. Also wrote a Facebook Messenger Chat Plug-in interface for Solvvy's chatbot platform.

Jul. 2018 - Sept. 2018

Graphic

Stanford Center for Design Research Research Assistant

Developed a model for automatic classification of dialogue acts in multiple-person design thinking team conversations by using Bidirectional Neural Networks.

Jun. 2017 - Jun. 2018

Graphic

Stanford CS106B ACE Head Teaching Assistant

I was in charge of CS106B ACE which is an extra section for more in-depth overview of C++ topics and class material.

Sept. 2018 - Jun. 2019

Graphic

Stanford Computer Science Research Assistant

Under the leadership of Stanford professor Silvio Savarese helped accomplish comprehensive 3D representation of indoor spaces by using multi-task convolutional neural networks trained on hundreds of thousands of indoor images

Summer 2016

Skills

Education

Stanford University

MS and BS in Computer Science (AI, Systems)

Projects

React Native Two Pane View for the Microsoft Surface Duo

I co-authored TwoPaneView for React Native which enables the dynamic rendering of Views on dual screen devices like the Microsoft Surface Duo. The GitHub repository can be found at Link and the npm package can be found at Link

Publications

RMM: A Recursive Mental Model for Dialog Navigation

RMM dramatically improves generated language questions and answers by recursively propagating reward signals.

Homero Roman Roman, Yonatan Bisk, Jesse Thomason, Asli Celikyilmaz, Jianfeng Gao

Photoshop 2.0: Generative Adversarial Networks for Photo Editing

By manipulating the encoded vector space of GANs it is possible to edit photos to add facial attributes.

Homero Roman Roman, Brandon Yang, Michelle Zhang

“Unmatched” Attention for Natural Language Inference

In this paper, we explore matrix-based attention weighting for improving attention models for Natural Language Inference.

Vinson Luo, Homero Roman Roman, Alex Tamkin

IDN Dialogue Act Classification With Conditional Random Fields and Recurrent Neural Networks

We set a new standard of accuracy for the task of dialogue act classification on the Interaction Dynamics Notation dataset through the use of Conditional Random Fields in addition to LSTM Recurrent Neural Networks.

Christopher Koenig, Homero Roman Roman, Amanda Lim

PDF

Automatic IDN Dialog Act Tagging of Design-Team Conversations

This paper explores the effectiveness of leveraging transfer learning in neural networks for the classification of conversations into their respective dialog acts. For this task, we use as our tags the Interaction Dynamics Notation (IDN) developed at the Stanford Center for Design Research.

Homero Roman Roman

PDF

Temporal Analysis of International Relations Networks

In this project, we explore structural properties of the alliance, war, and sentiment graphs of the the Correlates of War dataset, including the roles of individual nodes, structural motifs, and graph-level communities. In contrast to most previous work, we also explicitly analyze changes to the graphs over time.

Homero Roman Roman Colin P. Gaffney, Luis F. Varela

PDF

Automatic cancer development prediction based on classification of mass lesions in mammograms

In this project, diagnosis is done through multiclass classification of mamammographs into normal, benign, and cancerous while the prevention characterization is done by the automatic prediction of cancer development through reinforcement learning.

Homero Roman Roman

PDF

Contact