Athena (2021)

Our team is named Athena, after the Greek goddess of wisdom and strategy, because conversational AI systems need both knowledge and strategic dialogue management to be effective.

Coming straight from the redwoods of Santa Cruz, the Natural Language and Dialogue Systems Lab is making its fourth appearance in the competition. Our team is named Athena, after the Greek goddess of wisdom and strategy, because conversational AI systems need both knowledge and strategic dialogue management to be effective. Our scientific approach focuses on developing novel models for neural natural language generation and dialogue management. We will explore techniques in knowledge-grounded NLG as well as new models of dialogue coherence and response ranking that will mimic the human ability to follow-on a conversational turn with many different possible utterances.

Santa-Cruz-athena.jpg
Location: Santa Cruz, CA, USA
Faculty advisor: Marilyn Walker

Omkar P. - Team leader

Omkar is a second-year Computer Science & Engineering Master's student at UC Santa Cruz. He is currently working in Natural Language Processing with a focus on open-domain dialog systems under the supervision of Prof. Marilyn Walker. He has previously worked as a Software Engineer for three years on developing task-oriented chatbots for various customers in banking and telecommunication and is currently working on identifying customer churn indicators from health insurance transcripts as a part of his current internship. As a part of the Alexa Prize, He will be working on improving the NER and response generation capabilities of Athena.

Davan H.

Davan is a third-year PhD student who works with Professor Marilyn Walker in the Natural Language and Dialogue Systems Lab at the University of California Santa Cruz. His research interests lie in discourse modeling, dialogue systems, and neural language generation in the context of dialogue. His previous work includes sarcasm detection in online debate forums, stylistic variation in meaning to text generation, and automatic question generation. He competed in SGC3 as a member of Team Athena.

Juraj J.

Jurik is a fifth-year PhD student supervised by Professor Marilyn Walker in the Natural Language and Dialogue Systems lab. After getting his master's degree in AI at CTU in Prague, he moved to Santa Cruz to pursue a PhD in NLP. His current research at UCSC focuses on advancing deep-learning methods in natural language generation models for both task-oriented and open-domain dialogue systems, and he is the lead author of Slug2Slug, the winning system of the E2E NLG Challenge. Jurik's previous work includes context-aware language modeling, and making the language of chatbots more natural via stylistic control in neural models.

Lena R.

Lena was a member of the team for SGC3 where she contributed to our work on using knowledge graphs for DM and NLG, and developed response generators using AKG. Her research has focused on generalization and stylistic variation for neural natural language generation and automatically evaluating these outputs. She will further investigate the use of knowledge graphs in open domain dialogue systems to help generate responses using deep learning methods.

Kevin B.

Kevin is a fifth-year PhD student working in the Natural Language and Dialogue Systems laboratory under Professor Marilyn Walker at the University of California Santa Cruz. His primary research interest is dialogue, with a specific emphasis on user experience and personalization. Kevin has also worked on several key NLU modules in dialogue systems, e.g., NER, and dialogue generated with knowledge graphs. Being a 3-time participant and 2-time team lead in the previous Alexa Prize competitions, he is also familiar with the relevant AWS services and engineering tools required to build a scalable system.

Angela R.

Angela is a Natural Language Processing Master's Student at UCSC. Previously, she worked in the industry for over a year as data engineer, and 6 months prior was a data analyst. During her undergrad, she was a research assistant using analytics and visualizations to understand member and owner interactions in an online community, engineered different machine learning models to understand how individuals well being changed after using different well being applications, and used reinforcement learning to create 3 bots to play poker and simulated the game experience.

Jeshwanth B.

Jeshwanth is a master's student at the University of California, Santa Cruz in Natural Language Processing. His expertise is in NLP and backend development. He attended UC Santa Cruz for his undergrad as well, majoring in Computer Science and Minoring in Bioinformatics.

Eduardo Z.

I am an enthusiastic and passionate programmer with a drive for understanding and improvement. I always make sure to do my best on any project I am a part of so that I can not only contribute as an effective member of a team but also be proud of the work I accomplished. I also enjoy drawing and animating as a hobby, as well as play video games to relax. I hope my experiences and knowledge will help me succeed in both my career and life.

Phillip L.

I am a Master’s student in the NLP program at UCSC. My interests are in machine translation and text summarization. My number one hobby is cooking and I have also graduated from Le Cordon Bleu many years ago.

Rohan P.

Rohan is a UCSC sophomore with research interests in NLP, Reinforcement Learning, and Brain-Computer Interfaces. His past work in NLP includes sentiment analysis for mental health, question answering chatbots, multimodal sequence classification, and cognitively realistic syntax parsing. In the future, he’d like to investigate pragmatic theories of language through RL, advance semantic composition with neurosymbolic approaches, and apply linguistic RL to concrete tasks like neural program synthesis and web interaction. Outside of research, he runs UCSC’s neurotechnology club, attempts to build profitable micro-SaaS products, and enjoys reading Sanskrit philosophical literature.

Cecilia L.

Cecilia is a Master’s student in the Natural Language Processing program at UC Santa Cruz. She graduated from UC Santa Cruz with a B.S. in computer science and a minor in math. She is interested in Named Entity Recognition tasks and data analysis.

Marilyn Walker - Faculty advisor

Marilyn Walker is a Professor of Computer Science and a fellow of the Association for Computational Linguistics (ACL), in recognition of her fundamental contributions to statistical methods for dialog optimization, to centering theory, and to expressive natural language generation for dialog. Before coming to Santa Cruz in 2009, Walker was a professor of computer science at the University of Sheffield, and a research scientist AT&T Labs Research, where she worked on spoken dialogue systems. Walker has published more than 200 papers and has 10 U.S. patents granted or pending. She earned PhD in Computer Science at the University of Pennsylvania.

Latest news

The latest updates, stories, and more about Alexa Prize.
US, NY, New York
We are seeking a Robotics/AI Motor Control Scientist to develop cutting-edge machine learning algorithms for motor control systems in robots. In this role, you will focus on creating and optimizing intelligent motor control strategies to enable robots to perform complex, whole-body tasks. Your contributions will be essential in advancing robotics by enabling fluid, reliable, and safe interactions between robots and their environments. Key job responsibilities - Develop controllers that leverage reinforcement learning, imitation learning, or other advanced AI techniques to achieve natural, robust, and adaptive motor behaviors - Collaborate with multi-disciplinary teams to integrate motor control systems with robotic hardware, ensuring alignment with real-world constraints such as actuator dynamics and energy efficiency - Use simulation and real-world testing to refine and validate control algorithms - Stay updated on advancements in robotics, AI, and control systems to apply advanced techniques to robotic motion challenges - Lead technical projects from conception through production deployment - Mentor junior scientists and engineers - Bridge research initiatives with practical engineering implementation About the team Fauna Robotics, an Amazon company, is building capable, safe, and genuinely delightful robots for everyday life. Our goal is simple: make robots people actually want to live and interact with in everyday human spaces. We believe that future won’t arrive until building for robotics becomes far more accessible. Today, too much effort is spent reinventing the fundamentals. We’re changing that by developing tightly integrated hardware and software systems that make it faster, safer, and more intuitive to create real-world robotic products. Our work spans the full stack: mechanical design, control systems, dynamic modeling, and intelligent software. The focus is not just functionality, but experience. We’re building robots that feel responsive, expressive, and genuinely useful. At Fauna, you’ll work at the frontier of this space, helping define how robots move, manipulate, and interact with people in natural environments. It’s an opportunity to solve hard problems across hardware and software with a team focused on making robotics accessible and joyful to build. If you care about making robotics real for everyone and building systems that are as delightful as they are capable, we’re interested in hearing from you. an opportunity to solve hard problems across hardware and software with a team focused on making robotics accessible and joyful to build. If you care about making robotics real for everyone and building systems that are as delightful as they are capable, we’re interested in hearing from you.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists in the Forecasting, Macroeconomics & Finance field document, interpret and forecast Amazon business dynamics. This track is well suited for economists adept at combining times-series statistical methods with strong economic analysis and intuition. This track could be a good fit for candidates with research experience in: macroeconometrics and/or empirical macroeconomics; international macroeconomics; time-series econometrics; forecasting; financial econometrics and/or empirical finance; and the use of micro and panel data to improve and validate traditional aggregate models. Economists at Amazon are expected to work directly with our senior management and scientists from other fields on key business problems faced across Amazon, including retail, cloud computing, third party merchants, search, Kindle, streaming video, and operations. The Forecasting, Macroeconomics & Finance field utilizes methods at the frontier of economics to develop formal models to understand the past and the present, predict the future, and identify relevant risks and opportunities. For example, we analyze the internal and external drivers of growth and profitability and how these drivers interact with the customer experience in the short, medium and long-term. We build econometric models of dynamic systems, using our world class data tools, formalizing problems using rigorous science to solve business issues and further delight customers.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists at Amazon partner closely with senior management, business stakeholders, scientist and engineers, and economist leadership to solve key business problems ranging from Amazon Web Services, Kindle, Prime, inventory planning, international retail, third party merchants, search, pricing, labor and employment planning, effective benefits (health, retirement, etc.) and beyond. Amazon Economists build econometric models using our world class data systems and apply approaches from a variety of skillsets – applied macro/time series, applied micro, econometric theory, empirical IO, empirical health, labor, public economics and related fields are all highly valued skillsets at Amazon. You will work in a fast moving environment to solve business problems as a member of either a cross-functional team embedded within a business unit or a central science and economics organization. You will be expected to develop techniques that apply econometrics to large data sets, address quantitative problems, and contribute to the design of automated systems around the company.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists at Amazon partner closely with senior management, business stakeholders, scientist and engineers, and economist leadership to solve key business problems ranging from Amazon Web Services, Kindle, Prime, inventory planning, international retail, third party merchants, search, pricing, labor and employment planning, effective benefits (health, retirement, etc.) and beyond. Amazon Economists build econometric models using our world class data systems and apply approaches from a variety of skillsets – applied macro/time series, applied micro, econometric theory, empirical IO, empirical health, labor, public economics and related fields are all highly valued skillsets at Amazon. You will work in a fast moving environment to solve business problems as a member of either a cross-functional team embedded within a business unit or a central science and economics organization. You will be expected to develop techniques that apply econometrics to large data sets, address quantitative problems, and contribute to the design of automated systems around the company.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists at Amazon partner closely with senior management, business stakeholders, scientist and engineers, and economist leadership to solve key business problems ranging from Amazon Web Services, Kindle, Prime, inventory planning, international retail, third party merchants, search, pricing, labor and employment planning, effective benefits (health, retirement, etc.) and beyond. Amazon Economists build econometric models using our world class data systems and apply approaches from a variety of skillsets – applied macro/time series, applied micro, econometric theory, empirical IO, empirical health, labor, public economics and related fields are all highly valued skillsets at Amazon. You will work in a fast moving environment to solve business problems as a member of either a cross-functional team embedded within a business unit or a central science and economics organization. You will be expected to develop techniques that apply econometrics to large data sets, address quantitative problems, and contribute to the design of automated systems around the company.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists at Amazon partner closely with senior management, business stakeholders, scientist and engineers, and economist leadership to solve key business problems ranging from Amazon Web Services, Kindle, Prime, inventory planning, international retail, third party merchants, search, pricing, labor and employment planning, effective benefits (health, retirement, etc.) and beyond. Amazon Economists build econometric models using our world class data systems and apply approaches from a variety of skillsets – applied macro/time series, applied micro, econometric theory, empirical IO, empirical health, labor, public economics and related fields are all highly valued skillsets at Amazon. You will work in a fast moving environment to solve business problems as a member of either a cross-functional team embedded within a business unit or a central science and economics organization. You will be expected to develop techniques that apply econometrics to large data sets, address quantitative problems, and contribute to the design of automated systems around the company.
US, WA, Seattle
Economists in the Forecasting, Macroeconomics & Finance field document, interpret and forecast Amazon business dynamics. This track is well suited for economists adept at combining times-series statistical methods with strong economic analysis and intuition. This track could be a good fit for candidates with research experience in: macroeconometrics and/or empirical macroeconomics; international macroeconomics; time-series econometrics; forecasting; financial econometrics and/or empirical finance; and the use of micro and panel data to improve and validate traditional aggregate models. Economists at Amazon are expected to work directly with our senior management and scientists from other fields on key business problems faced across Amazon, including retail, cloud computing, third party merchants, search, Kindle, streaming video, and operations. The Forecasting, Macroeconomics & Finance field utilizes methods at the frontier of economics to develop formal models to understand the past and the present, predict the future, and identify relevant risks and opportunities. For example, we analyze the internal and external drivers of growth and profitability and how these drivers interact with the customer experience in the short, medium and long-term. We build econometric models of dynamic systems, using our world class data tools, formalizing problems using rigorous science to solve business issues and further delight customers.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists at Amazon partner closely with senior management, business stakeholders, scientist and engineers, and economist leadership to solve key business problems ranging from Amazon Web Services, Kindle, Prime, inventory planning, international retail, third party merchants, search, pricing, labor and employment planning, effective benefits (health, retirement, etc.) and beyond. Amazon Economists build econometric models using our world class data systems and apply approaches from a variety of skillsets – applied macro/time series, applied micro, econometric theory, empirical IO, empirical health, labor, public economics and related fields are all highly valued skillsets at Amazon. You will work in a fast moving environment to solve business problems as a member of either a cross-functional team embedded within a business unit or a central science and economics organization. You will be expected to develop techniques that apply econometrics to large data sets, address quantitative problems, and contribute to the design of automated systems around the company.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists at Amazon partner closely with senior management, business stakeholders, scientist and engineers, and economist leadership to solve key business problems ranging from Amazon Web Services, Kindle, Prime, inventory planning, international retail, third party merchants, search, pricing, labor and employment planning, effective benefits (health, retirement, etc.) and beyond. Amazon Economists build econometric models using our world class data systems and apply approaches from a variety of skillsets – applied macro/time series, applied micro, econometric theory, empirical IO, empirical health, labor, public economics and related fields are all highly valued skillsets at Amazon. You will work in a fast moving environment to solve business problems as a member of either a cross-functional team embedded within a business unit or a central science and economics organization. You will be expected to develop techniques that apply econometrics to large data sets, address quantitative problems, and contribute to the design of automated systems around the company.
US, WA, Seattle
Amazon.com strives to be Earth's most customer-centric company where customers can shop in our stores to find and discover anything they want to buy. We hire the world's brightest minds, offering them a fast paced, technologically sophisticated and friendly work environment. Economists in the Forecasting, Macroeconomics & Finance field document, interpret and forecast Amazon business dynamics. This track is well suited for economists adept at combining times-series statistical methods with strong economic analysis and intuition. This track could be a good fit for candidates with research experience in: macroeconometrics and/or empirical macroeconomics; international macroeconomics; time-series econometrics; forecasting; financial econometrics and/or empirical finance; and the use of micro and panel data to improve and validate traditional aggregate models. Economists at Amazon are expected to work directly with our senior management and scientists from other fields on key business problems faced across Amazon, including retail, cloud computing, third party merchants, search, Kindle, streaming video, and operations. The Forecasting, Macroeconomics & Finance field utilizes methods at the frontier of economics to develop formal models to understand the past and the present, predict the future, and identify relevant risks and opportunities. For example, we analyze the internal and external drivers of growth and profitability and how these drivers interact with the customer experience in the short, medium and long-term. We build econometric models of dynamic systems, using our world class data tools, formalizing problems using rigorous science to solve business issues and further delight customers.