Bio

Federico Bianchi is a postdoctoral researcher at Stanford University. His research, ranging from Natural Language Processing methods for textual analytics to recommender systems for e-commerce has been accepted to major NLP and AI conferences (EACL, NAACL, EMNLP, ACL, AAAI, RecSys) and journals (Cognitive Science, Applied Intelligence, Semantic Web Journal).

Contact

  • Academic
    fede@stanford.edu
    University - Scholar Department: Computer Science Position: Postdoctoral Scholar

Additional Info

Links

All Publications

  • A challenge for rounded evaluation of recommender systems NATURE MACHINE INTELLIGENCE Tagliabue, J., Bianchi, F., Schnabel, T., Attanasio, G., Greco, C., Moreira, G., Chia, P. 2023

    View details for DOI 10.1038/s42256-022-00606-0

    View details for Web of Science ID 000920812400002

  • Viewpoint: Artificial Intelligence Accidents Waiting to Happen? JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH Bianchi, F., Curry, A., Hovy, D. 2023; 76: 193-199

    View details for Web of Science ID 000915402300001

  • Contrastive language and vision learning of general fashion concepts. Scientific reports Chia, P. J., Attanasio, G., Bianchi, F., Terragni, S., Magalhaes, A. R., Goncalves, D., Greco, C., Tagliabue, J. 2022; 12 (1): 18958

    Abstract

    The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models. While most use cases are cast as specialized supervised learning problems, we argue that practitioners would greatly benefit from general and transferable representations of products. In this work, we build on recent developments in contrastive learning to train FashionCLIP, a CLIP-like model adapted for the fashion industry. We demonstrate the effectiveness of the representations learned by FashionCLIP with extensive tests across a variety of tasks, datasets and generalization probes. We argue that adaptations of large pre-trained models such as CLIP offer new perspectives in terms of scalability and sustainability for certain types of players in the industry. Finally, we detail the costs and environmental impact of training, and release the model weights and code as open source contribution to the community.

    View details for DOI 10.1038/s41598-022-23052-9

    View details for PubMedID 36347888

  • "Does it come in black?" CLIP-like models are zero-shot recommenders Chia, P., Tagliabue, J., Bianchi, F., Greco, C., Goncalves, D., Assoc Computat Linguist ASSOC COMPUTATIONAL LINGUISTICS-ACL. 2022: 191-198

    View details for Web of Science ID 000846890000022

https://orcid.org/0000-0003-0776-361X