Daniel Valcarce

Software Engineer

About me

my image

Daniel Valcarce

Hi! My name is Daniel. I am a software engineer at Google in Zürich. I am currently working on making the Google Assistant smarter using machine intelligence technology.

My research interests cover recommender systems, information retrieval, machine learning and natural language processing. Before working at Google, I did my PhD at the Information Retrieval Lab of the University of A Coruña. My PhD thesis explored the relationships between information retrieval and recommender systems fields.

Updated: Jun 21, 2020.

My resume

Experience

2019 - now

Software Engineeer (Google)

from June 2019 to present day

Zürich, Switzerland

Working on machine intelligence technology to make the Google Assistant smarter.

2015 - 2019

PhD Fellow

from September 2015 to present day

At the Department of Computer Science of the University of A Coruña

Worked on my PhD thesis under the support of a FPU fellowship, the most competitive grant from the Spanish Government that funds the development of a PhD thesis during four years. During this period, I was also a Lab Instructor for several BSc and MSc courses: Information Retrieval, Information Retrieval and the Semantic Web, Operating Systems, Software Developer Tools, and Software Methodologies.

2018

Software Engineer Intern (Google)

from May 2018 to August 2018

At Google's Meeting Room Intelligence team in Munich, Germany

During this software engineering internship, I worked with the Meeting Room Intelligence team developing solutions to improve Google's meeting technologies.

2017

Research Visitor (UAM)

from April 2017 to June 2017

At the IR Group at the UAM in Madrid, Spain

3-month research stay funded by the Spanish Government at the Information Retrieval Group (UAM) under the supervision of Pablo Castells. I studied the applicability of information retrieval evaluation metrics to recommendation.

2016

Research Visitor (ISTI-CNR)

from April 2016 to June 2016

At the HPC Lab from ISTI-CNR in Pisa, Italy

3-month research stay funded by the Spanish Government at the High Performance Computing Lab (ISTI-CNR) under the supervision of Raffaele Perego. I worked on novel recommendation tasks and on the adaptation of learning to rank techniques to recommendation.

2014 - 2015

Research Assistant

from April 2014 to April 2015

At the Information Retrieval Lab of the University of A Coruña

Hired by the IRLab to work on distributed recommender systems for big data environments using MapReduce and NoSQL technologies. I also focused on studying and improving accuracy, diversity and novelty of different approaches to recommendation.

2013 - 2014

Collaboration Fellowship

from November 2013 to July 2014

At the Department of Computer Science of the University of A Coruña

Competitive grant from the Spanish Government for outstanding students that are interested in pursuing an academic career in the last year of their degrees.

Developed a distributed recommendation platform with several collaborative filtering algorithms using Hadoop and Cassandra, Django, Lucene, Memcached and Varnish.

Education

2014 - 2019

PhD in Computer Science

from November 2014 to May 2019

At the University of A Coruña (Spain)

PhD thesis: Information Retrieval Models for Recommender Systems.

Advisors: Álvaro Barreiro and Javier Parapar.

Grade: Sobresaliente cum laude (highest grade).


Extraordinary PhD Award

Distinction given by the University of A Coruña to the best PhD theses defended at this university.

SCIE-BBVA Award

Won the Young Researcher Modality of the Research Awards given by the Spanish Computer Science Society and the BBVA Foundation in 2020: press note.

2009 - 2014

BSc+MSc in Computer Science

from October 2009 to July 2014

At the University of A Coruña (Spain)

Grade: 9.32/10 (with honours)


Final project: Distributed Platform For Movie Recommendation

A distributed recommender platform capable of making personalised recommendations using collaborative filtering techniques in a big data environment.

Grade: 10/10 (with honours)


Outstanding Graduate Award, University of A Coruña

Valedictorian distinction given by the University of A Coruña to the students, one for each degree, with the best marks among all the graduates that finished their studies in 2014 at the University of A Coruña.

Outstanding Graduate Award, Xunta de Galicia

Valedictorian distinction given by the Reginal Government of Galicia to the students, one for each degree, with the best marks among all the graduates that finished their studies in 2014 in the Galicia region.

National Outstanding Graduate Award, Ministerio de Educación

Distinction was given by the Spanish Ministry of Education to those students with the best marks among all the graduates that finished their studies in 2014 in Spain.

Publications

Daniel Valcarce, Alejandro Bellogín, Javier Parapar, Pablo Castells. Assessing ranking metrics in top-N recommendation. Information Retrieval Journal, 2020. DOI 10.1007/s10791-020-09377-x.
Alfonso Landin, Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Shallow Neural Models for Top-N Recommendation. Proceedings of the 24th European Conference on Artificial Intelligence, ECAI 2020, pp. 2911-2912, Santiago de Compostela, Spain, 29 August - 8 September, 2020. DOI 10.3233/FAIA200449.
Anabella Barsaglini-Castro, Daniel Valcarce. The Coruña corpus tool: Ten years on. Procesamiento del Lenguaje Natural, vol. 64, pp. 13-19, 2020.
Daniel Valcarce. Information Retrieval Models for Recommender Systems. Doctoral Thesis, Universidade da Coruña, 2019. Slides
Daniel Valcarce, Alfonso Landin, Javier Parapar, Álvaro Barreiro. Collaborative filtering embeddings for memory-based recommender systems. Engineering Applications of Artificial Intelligence, vol. 85, pp. 347-356, 2019. DOI 10.1016/j.engappai.2019.06.020.
Alfonso Landin, Daniel Valcarce, Javier Parapar, Álvaro Barreiro. PRIN: A Probabilistic Recommender with Item Priors and Neural Models. Proceedings of the 41st European Conference on Information Retrieval, ECIR 2019, pp. 133-147, Cologne, Germany, 14 - 18 April, 2019. DOI 10.1007/978-3-030-15712-8_9.
David Otero, Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Building High-Quality Datasets for Information Retrieval Evaluation at a Reduced Cost. Proceedings 2019, vol. 21(1), 33. DOI 10.3390/proceedings2019021033.
Alfonso Landin, Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Priors for Diversity and Novelty on Neural Recommender Systems. Proceedings 2019, vol. 21(1), 20. DOI 10.3390/proceedings2019021020.
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Document-based and Term-based Linear Methods for Pseudo-Relevance Feedback. Applied Computing Review, vol. 18(4), pp. 5-17, 2018.
Daniel Valcarce, Igo Brilhante, Jose Antonio Macedo, Franco Maria Nardini, Raffaele Perego, Chiara Renso. Item-driven group formation. Online Social Networks and Media, vol. 8, pp. 17-31, 2018. DOI 10.1016/j.osnem.2018.10.002
Daniel Valcarce, Alex Bellogín, Javier Parapar, Pablo Castells. On the Robustness and Discriminative Power of IR Metrics for Top-N Recommendation. Proceedings of the 12th ACM Conference on Recommender Systems, RecSys 2018, pp. 260-268, Vancouver, Canada, 2 - 7 October, 2018. DOI 10.1145/3240323.3240347 Slides Poster
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Finding and Analysing Good Neighbourhoods to Improve Collaborative Filtering. Knowledge-Based Systems, vol. 159, pp. 193-202, 2018. DOI 10.1016/j.knosys.2018.06.030
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. A MapReduce implementation of posterior probability clustering and relevance models for recommendation. Engineering Applications of Artificial Intelligence, vol. 75, pp. 114-124, 2018. DOI 10.1016/j.engappai.2018.08.006
Alfonso Landin, Eva Suárez-García, Daniel Valcarce. When Diversity Met Accuracy: A Story of Recommender Systems. Proceedings 2018, vol. 2(8), 1178. DOI 10.3390/proceedings2181178
Eva Suárez-García, Alfonso Landin, Daniel Valcarce, Álvaro Barreiro. Term Association Measures for Memory-based Recommender Systems. Proceedings of the 5th Spanish Conference on Information Retrieval, CERI 2018, Article 6, Zaragoza, Spain, 25 - 27 June, 2018. DOI 10.1145/3230599.3230606 Best Student Paper
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Query Expansion as a Matrix Factorization Problem: Extended Abstract. Proceedings of the 5th Spanish Conference on Information Retrieval, CERI 2018, Article 6, Zaragoza, Spain, 25 - 27 June, 2018. DOI 10.1145/3230599.3230603
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. LiMe: Linear Methods for Pseudo-Relevance Feedback. Proceedings of the 33st Annual ACM Symposium on Applied Computing, SAC 2018, pp. 678-687, Pau, France, 9 - 13 April, 2018. DOI 10.1145/3167132.3167207 Slides
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Axiomatic Analysis of Language Modelling of Recommender Systems. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 25, no suppl. 2, pp. 113-128, 2017. DOI 10.1142/S0218488517400141
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Combining Top-N Recommenders with Metasearch Algorithms. Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, SIGIR 2017, pp. 805-808, Shinjuku, Tokyo, Japan, 7 - 11 August, 2017. DOI 10.1145/3077136.3080647 Poster
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Additive Smoothing for Relevance-Based Language Modelling of Recommender Systems. Proceedings of the 4th Spanish Conference on Information Retrieval, CERI 2016, Article 9, Granada, Spain, 14 - 16 June, 2016. DOI 10.1145/2934732.2934737 Slides Best Student Paper
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Computing Neighbourhoods with Language Models in a Collaborative Filtering Scenario. Proceedings of the 7th Italian Information Retrieval Workshop, IIR 2016, Venice, Italy, 30 - 31 May, 2016. Original at CEUR-WS Slides
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Item-Based Relevance Modelling of Recommendations for Getting Rid of Long Tail Products. Knowledge-Based Systems, vol. 103, pp. 41-51, 2016. DOI 10.1016/j.knosys.2016.03.021
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Efficient Pseudo-Relevance Feedback Methods for Collaborative Filtering Recommendation. Proceedings of the 38th European Conference on Information Retrieval, ECIR 2016, pp. 602-613, Padua, Italy, 20 - 23 March, 2016. DOI 10.1007/978-3-319-30671-1_44 Slides
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. Language Models for Collaborative Filtering Neighbourhoods. Proceedings of the 38th European Conference on Information Retrieval, ECIR 2016, pp. 614-625, Padua, Italy, 20 - 23 March, 2016. DOI 10.1007/978-3-319-30671-1_45 Slides
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. A Distributed Recommendation Platform for Big Data. Journal of Universal Computer Science, vol. 21(13), pp. 1810-1829, 2015. DOI 10.3217/jucs-021-13-1810
Daniel Valcarce. Exploring Statistical Language Models for Recommender Systems. Proceedings of the 9th ACM Conference on Recommender Systems, RecSys 2015, pp. 375-378, Vienna, Austria, 16 - 20 September, 2015. DOI 10.1145/2792838.2796547 Slides Poster
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. A Study of Priors for Relevance-Based Language Modelling of Recommender Systems. Proceedings of the 9th ACM Conference on Recommender Systems, RecSys 2015, pp. 237-240, Vienna, Austria, 16 - 20 September, 2015. DOI 10.1145/2792838.2799677 Poster
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. A Study of Smoothing Methods for Relevance-Based Language Modelling of Recommender Systems. Proceedings of the 37th European Conference on Information Retrieval, ECIR 2015, pp. 346-351, Vienna, Austria, 29 March - 2 April, 2015. DOI 10.1007/978-3-319-16354-3_38 Poster
Daniel Valcarce, Javier Parapar, Álvaro Barreiro. When Recommenders Met Big Data: an Architectural Proposal and Evaluation. Proceedings of the 3rd Spanish Conference on Information Retrieval, CERI 2014, pp. 73-84, A Coruña, Spain, 19 - 20 June, 2014. ISBN 978-84-9749-591-2 Slides

Other Courses

Deep Learning
Deep Learning

Coursera - deeplearning.ai specialization on Deep Learning taught by Prof. Andrew Ng in 2017-2018.

Probabilistic Graphical Models
Probabilistic Graphical Models

Stanford Coursera specialization on Probabilistic Graphical Models taught by Dr. Daphne Koller in 2016-2017.

Writing in the Sciences
Writing in the Sciences

Stanford Lagunita course on MWriting in the Sciences taught by Dr. Kristin Sainani in 2015.

Mining of Massive Datasets
Mining of Massive Datasets

Stanford Coursera course on Mining of Massive Datasets taught by Dr. Jure Leskovec, Dr. Anand Rajaraman and Prof. Jeffrey Ullman in 2015.

MLSS2014
MLSS2014

2014 edition of the Machine Learning Summer School at Carnegie Mellon University (Pittsburgh, PA) organised by Prof. Alex Smola and Dr. Zico Kolter.

Statistical Learning
Statistical Learning

Stanford Lagunita course on Statistical Machine Learning taught by Prof. Trevor Hastie and Prof. Rob Tibshirani in 2014.

Learning From Data
Learning From Data

Caltech edX course on theoretical and applied Machine Learning taught by Prof. Yaser S. Abu-Mostafa in 2013.

Algorithms: Design and Analysis Part 1 & 2
Algorithms: Design and Analysis Part 1 & 2

Stanford Coursera courses on algorithm design and analysis taught by Dr. Tim Roughgarden in 2013.

Model Thinking
Model thinking

Michigan Coursera course on model design taught by Prof. Scott E. Page in 2012.

Quantum Mechanics and Quantum Computation
Quantum Mechanics and Quantum Computation

Berkeley Coursera course on Quantum Computing taught by Prof. Umesh V. Vazirani in 2012.

Machine Learning
Machine Learning

Stanford Coursera course on Machine Learning foundations taught by Dr. Andrew Ng in 2012.

Introduction to Artificial Intelligence
Introduction to Artificial Intelligence

Udacity course on Artifical Intelligence foundations taught by Prof. Peter Norvig and Prof. Sebastian Thrun in 2011.

Contact