Josep Valls-Vargas

I am a machine learning engineer specializing on NLP and deep learning working with the search and Sensei teams at Adobe. I am working on search and recommendation solutions using knowledge graphs and highly-scalable technology. Before Adobe, I was an applied scientist working on dialog management with the Alexa science team at Amazon where I researched mechanisms for continuous learning for dialog management systems.

I received my PhD from the Department of Computer Science at Drexel University under the supervision of Dr. Santiago Ontañón Villar and Dr. Jichen Zhu. My research focused on topics related to natural language understanding and generation, computational narrative, experience management, user modeling and procedural content generation in the application domain of digital entertainment.

Previously, I received a M.S. in Computer Science from Drexel University in 2014, a M.S. in Artificial Intelligence and Computer Vision from UAB/IIIA-CSIC in 2011, and a B.S. in Computer Science from Universitat Autònoma de Barcelona in 2010.

email: josep@valls.name

Selected Publications

P. K. Bodigutla, A. Tiwari, J. Valls-Vargas, L. Polymenakos, S. Matsoukas (2020). Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations. To appear in Findings of EMNLP 2020. [PDF]
J. Valls-Vargas, J. Zhu, S. Ontañón (2017). Narrative Information Extraction with Non-Linear Natural Language Processing Pipelines. PhD thesis at Drexel University. [PDF]
J. Valls-Vargas, J. Zhu and S. Ontañón (2017). Towards End-to-end Natural Language Story Generation Systems. INT 2017. [AAAI]
J. Valls-Vargas, J. Zhu and S. Ontañón (2017). Graph Grammar-based Controllable Generation of Puzzles for a Learning Game about Parallel Programming. FDG 2017.
J. Valls-Vargas, J. Zhu, S. Ontañón (2017). From Computational Narrative Analysis to Generation: A Preliminary Review. FDG 2017. [Poster]
J. Valls-Vargas, J. Zhu, S. Ontañón (2017). Towards Automatically Extracting Story Graphs from Natural Language Stories. AAAI WNAIG 2017 [AAAI]
S. Ontañón, J. Valls-Vargas, J. Zhu (2017). Bridging the Gap Between Computational Narrative and Natural Language Processing (position). AAAI WNAIG 2017 [AAAI]
J. Valls-Vargas, J. Zhu, S. Ontañón (2016). Predicting Proppian Narrative Functions from Stories in Natural Language. AIIDE 2016. [PDF]
J. Valls-Vargas, J. Zhu, S. Ontañón (2016). Error Analysis in an Automated Narrative Information Extraction Pipeline. IEEE Transactions on Computational Intelligence and AI in Games. [IEEE]
J. Valls-Vargas, S. Ontañón, J. Zhu (2015). Exploring Player Trace Segmentation for Dynamic Play Style Prediction. AIIDE 2015. [PDF PPT]
J. Valls-Vargas, J. Zhu, S. Ontañón (2015). Narrative Hermeneutic Circle: Improving Character Role Identification from Natural Language Text via Feedback Loops. IJCAI 2015. [PDF]
J. Valls-Vargas, A. Kahl, J. Patterson, G. Muschio, A. Foster, J. Zhu (2015). Designing and Tracking Play Styles in Solving the Incognitum. GLS 2015. [PDF pp. 241-247]
J. Valls-Vargas, J. Zhu, S. Ontañón (2014). Toward Automatic Role Identification in Unannotated Folk Tales. AIIDE 2014. [PDF PPT Poster]
J. Valls-Vargas, S. Ontañón, J. Zhu (2014). Toward Automatic Character Identification in Unannotated Narrative Text. INT 7 at ELO 2014. [PDF]
J. Valls-Vargas, S. Ontañón, J. Zhu (2013). Toward Character Role Assignment for Natural Language Stories. INT6 at AIIDE 2013. [PPT PDF]
J. Valls-Vargas, S. Ontañón, J. Zhu (2013). Towards Story-Based Content Generation: From Plot-Points to Maps. In CIG 2013. [PPT PDF (mirror)]
Josep Valls-Vargas and Santiago Ontañón (2012). Natural Language Generation through Case-based Text Modification. In ICCBR 2012. [SpringerLink]
Josep Valls-Vargas and Santiago Ontañón (2011). Text Modification Methods for Natural Language Generation. Master's thesis at UAB. [PDF]

Other Publications

Alderfer, K.B., Smith, B.K., Ontañón, S., Char, B., Nebolsky, J., Zhu, J., Furqan, A., Freed, E., Patterson, J. and Valls-Vargas, J., (2018). Lessons Learned From an Interactive Educational Computer Game About Concurrent Programming. ACM Technical Symposium on Computer Science Education [ACM]
Santiago Ontañón, Bruce Char, Jichen Zhu, Evan Freed, Brian K. Smith, Anushay Furqan, Michael Howard, Anna Nguyen, Justin Patterson, and Josep Valls-Vargas (2017). Designing Visual Metaphors for an Educational Game for Parallel Programming. SIGCHI Play 2017 [PDF]
Natalie Lyon, Josep Valls, Caroline Guevara, Ning Shao, Junyu Zhu, Jichen Zhu (2014). Little Newton: an educational physics game. SIGCHI Play 2014. [PDF]

Presentations

Amazon Future Engineer class chats. Presentation and Q&A session with K-12 students. 2020-2021.
User Satisfaction Estimation. Alexa Prize Summit 2020 (cancelled due to covid-19)
Narrative Information Extraction with Non-Linear Natural Language Processing Pipelines. PhD thesis defense at Drexel University. 2017-12-05.
Graph Grammar-based Controllable Generation of Puzzles for a Learning Game about Parallel Programming. 2017-08-16 FDG 2017.
Bridging the Gap Between Computational Narrative and Natural Language Processing (position) and Towards Automatically Extracting Story Graphs from Natural Language Stories. 2017-02-04 AAAI 2017 Workshop on What's next for AI in games.
Predicting Proppian Narrative Functions from Stories in Natural Language. 2016-10-10 AIIDE 2016.
Requiem for a theory: the ‘story grammar’ story. 2016-10-05 Narrative readings group.
Automated Narrative Information Extraction Using Non-Linear Pipelines. 2016-07-12 IJCAI Doctoral Consortium.
What is Artificial Intelligence? UPE Ex Machina movie screening and discussion. [Online]
Automated Narrative Information Extraction Using Non-Linear Pipelines (work-in-progress). 2016-04-01 Mid-Atlantic Student Colloquium on Speech, Language and Learning (MASC-SLL)
Procedural Content Generation (for videogames). 2016-01-26 Entrepreneurial Game Studio. [Online]
Introduction to Player Modeling. 2015-07-14 AI&G Lunch presentation.
Player Modeling. Literature Review for TAEMILE. 2015-04-13.
Approaches to Storytelling and Creativity. 2015-03-03 AI&G.
Introduction to Weka. 2014-12-03 AI&G Lunch presentation.
Extraction of Computational Models of Narrative from Natural Language. 2014-06-12 Candidacy Defense.
Narrative Extraction, Processing and Generation for Interactive Fiction and Computer Games. 2013-10-18 Doctoral Consortium at AIIDE 2013.
A Case-Based Reasoning Approach to Text Generation. 2013-07-08 Doctoral Consortium at ICCBR 2013.
Story-Based Map Generation. 2013-04-18 Drexel Research Day 2013.
Text Modification Methods for Natural Language Generation. 2012-09-05 Master's thesis.

Projects

Voz, a system that explores techniques for automatic extraction of narrative information from text. Josep Valls, Santiago Ontañon, Jichen Zhu.
Parallel, NSF-funded project that explores teaching of parallel programming topics and personalized content generation. PI: Santiago Ontañón, Co-PI: Brian Smith, Jichen Zhu, Bruce Char.
TAEMILE, NSF-funded project examining how game AI, integrated with play-based pedagogy, can facilitate learning in interactive environment. PI: Jichen Zhu, Co-PI: Glen J. Muschio, Aroutis N. Foster.
ask.py: A lightweight template and utilities for developing skills for the Amazon Alexa Skill Kit and Cortana using Python.
Story2Map, a map generator for stories from a story space defined as plot points.
Case Based Text Adaptation (CeBeTA), a text realization module to improve the output of the Riu interactive narrative system
Little Newton, an educational physics-based game. [PDF]
Co-founder, R&D, AI, software architecture consultant at Referup S.L., www.sntalent.com; talentclue.com.
Referup/SNTalent (bachelor's thesis [PDF])

More...

Community Involvement

Reviewer/subreviewer:
- AMLC (Amazon ML Conference, internal) 2018, 2019, 2020
- IEEE Transactions on Games 2019, 2020
- ICCC 2017
- WNAIG 2017
- IJCAI 2016
- AAMAS 2016
- AIIDE 2015
- INT8 2015
- FDG 2015
- ICIDS 2013
Organizer of the Drexel NLP reading group 2015-2017.
Treasurer, activity coordinator. Drexel Chapter of Upsilon Pi Epsilon International Honor Society for the Computing and Information Disciplines. 2014-2016.
Graduate student representative in the dean search committee for the College of Computing and Informatics at Drexel University. March 2016.
Graduate student representative in the task force for the creation of the College of Computing and Informatics at Drexel University. July 2013.

Teaching and Mentoring

Volunteer for Amazon Future Engineer (democratizing access to computer science in K-12 education)
Mentor for the Amazon Day 1 program (applied scientist mentoring, internal) 2019-2020.
Tutor for Cambridge Schools Volunteers 2019-2021.
Mentor for PhillyCodefest 2017.
Teaching assistant at Drexel University
- Graduate student mentor for the REThink program (Research Experiences for Teachers in Engineering and Computer Science) (Summer 2015)
- CS 338 - Graphical User Interfaces (Winter 2015)
- CS 140 - Multimedia Programming (Fall 2014)
- Drexel University Computing Academy (Summer 2013)
- CS 171 - Computer Programming I (Winter 2013)
- CS 164 - Introduction to Computer Science (Fall 2012)