Federico Bianchi

Federico Bianchi

Postdoctoral Researcher

Bocconi University

Biography

Hello! I am Federico Bianchi, a post-doctoral researcher at Bocconi University (with Prof. Dirk Hovy), Milan, Italy.

You can find my work in the main track of different AI venues (e.g., NAACL, EACL, AAAI, ACL, ISWC, RecSys) and Q1 Journals (e.g., Cognitive Science, Nature PJQI, SWJ) and a few things have also been featured in press or in company media outlets (see, 1, 2, 3, 4).

I have different interests that range from neuro-symbolic learning and reasoning to natural language processing and from quantum physics to deep learning for the e-commerce.

I have also worked/collaborated with companies: I have collaborated as a Data Scientist for Instal LLC and I have an ongoing research collaboration with people at Coveo on e-commerce and recommendation research. In the past, I worked as a full-stack software developer for Mobave LLC (later acquired by Instal) and for Whattaspot.

Interests
  • Artificial Intelligence
  • Computational Linguistics
  • Cats
  • Emacs
  • Reasoning
Education

  • PhD in Computer Science, 2020

    University of Milano-Bicocca

  • MSc in Computer Science, 2016

    University of Milano-Bicocca

  • BSc in Computer Science, 2014

    University of Milano-Bicocca

Featured Publications

Giovanni Cassani, Federico Bianchi, Marco Marelli
April 2021 In Cognitive Science
Words with Consistent Diachronic Usage Patterns are Learned Earlier: A Computational Analysis Using Temporally Aligned Word Embeddings.
Words with Consistent Diachronic Usage Patterns are Learned Earlier: A Computational Analysis Using Temporally Aligned Word Embeddings.

In this study, we use temporally aligned word embeddings and a large diachronic corpus of English to quantify language change in a data‐driven, scalable way, which is grounded in language use.
PDF Cite Code Tweet
Federico Bianchi, Ciro Greco, Jacopo Tagliabue
March 2021 In NAACL-HLT
Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction
Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction

We investigate grounded language learning through real-world data, by modelling a teacher-learner dynamics through the natural interactions occurring between users and search engines.
PDF Cite Code Tweet
Federico Bianchi, Silvia Terragni, Dirk Hovy, Debora Nozza, Elisabetta Fersini
March 2021 In EACL
Cross-lingual Contextualized Topic Models with Zero-shot Learning
Cross-lingual Contextualized Topic Models with Zero-shot Learning

We introduce a novel topic modeling method that can make use of contextulized embeddings (e.g., BERT) to do zero-shot cross-lingual topic modeling.
PDF Cite Code Slides Blog Post
Valerio Di Carlo, Federico Bianchi, Matteo Palmonari
July 2019 In AAAI.
Training Temporal Word Embeddings with a Compass
Training Temporal Word Embeddings with a Compass

We introduce a novel model for word embedding alignment and test it on temporal word embeddings obtaining SOTA results.
PDF Cite Code Blog Post

Research Philosophy

I think scientific research should be easy to access and to replicate. You can find most of my papers on ArXiv and on open access platforms - unfortunately, this is not always possible. The code I write is available online and I try to make it easy to use so that everyone can benefit from it.

I also try to actively participate in scientific communication. I have many blog posts online, explaining different research topics to the public and I am also part of the ComIntArt (Comitato Intelligenza Artificiale) where I do videos for the Italian public (see for example, this video on GPT-3 limits).

Recent & Upcoming Talks

Talk: Deep Learning for Quantum Problems
We introduce the main components present in deep learning architecture and the possible applications in quantum physics.
Mar 23, 2021 1:00 PM University of Milan
Federico Bianchi, Adriano Macarone
Follow
Talk: Deep Learning for Quantum Problems
Talk: Fantastic Embeddings and How to Align Them
In this talk I present our paper on aligning product embeddings that come from multiple shops. We use techniques from machine translation to provide an effective method for alignment.
Mar 23, 2021 1:00 PM SIGIR (Virtual)
Federico Bianchi
PDF Video Follow
Talk: Fantastic Embeddings and How to Align Them
Talk: Learning JAX for Great Good
I gave a tutorial on JAX, the new google framework for deep learning. I have described how to compute simple derivatives and finished describing some applications in NLP.
Feb 17, 2021 1:00 PM Coveo Labs
Federico Bianchi
Follow
Talk: Learning JAX for Great Good
Talk: Vector Space Alignment for Semantic Change Analysis
The use of compass aligned embeddings for semantic change analysis.
Oct 7, 2020 1:00 PM — 3:00 PM Tilburg University
Federico Bianchi
Follow
Talk: Vector Space Alignment for Semantic Change Analysis
Talk: On the Capabilities of Logic Tensor Networks for Deductive Reasoning
I presented our work on Logic Tensor Networks, where we explore its reasoning capabilities.
Mar 1, 2019 1:00 PM AAAI-MAKE
Federico Bianchi
PDF Code Follow
Talk: On the Capabilities of Logic Tensor Networks for Deductive Reasoning

Recent Publications

Quickly discover relevant content by filtering publications. You can also look at my Google Scholar profile for an updated list of my publications.
Federico Bianchi, Giuseppe Attanasio, Raphael Pisoni, Silvia Terragni, Gabriele Sarti, Sri Lakshmi (2021). Contrastive Language-Image Pre-training for the Italian Language. In ArXiv.

PDF Cite Code Demo

Federico Bianchi, Silvia Terragni, Dirk Hovy (2021). Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence. In ACL.

Cite Code

Federico Bianchi, Jacopo Tagliabue, Bingqing Yu (2021). Query2Prod2Vec: Grounded Word Embeddings for eCommerce. In NAACL-HLT.

PDF Cite Best Industry Paper Award

Tommaso Fornaciari, Federico Bianchi, Massimo Poesio, Dirk Hovy (2021). BERTective: Language Models and Contextual Information for Deception Detection. In EACL.

Cite

See all publications