Published inTowards Data Science·PinnedYour Vision-Language Model Might Be a Bag of WordsWe explore the limits of what vision-language models get about language in our Oral Paper at ICLR 2023 — Multimodal AI is the talk of the town. With the recent release of GPT-4, we are seeing myriads of new possible applications and future technologies that were unthinkable six months ago. Indeed, vision-language models in general are very useful for many different tasks. …Machine Learning8 min readMachine Learning8 min read
Published inTowards Data Science·PinnedTeaching CLIP Some FashionTraining FashionCLIP, a domain-specific CLIP model for Fashion — This is a short blog post describing FashionCLIP. If you are a data scientist you probably have to deal with both images and text. However, your data will be very specific to your domain, and standard models might not work well. …Machine Learning10 min readMachine Learning10 min read
Published inTowards Data Science·PinnedOn the Gap between Adoption and UnderstandingIssues with current research trends in NLP can hamper the free development of scientific research — This blog post describes our recent paper: Federico Bianchi and Dirk Hovy (2021). On the Gap between Adoption and Understanding in NLP. Findings of the Association for Computational Linguistics. Associations of Computational Linguistics (to appear). The main focus of this work is to describe issues that currently affect NLP research…NLP7 min readNLP7 min read
Published inTowards Data Science·Sep 19A Foundation Model for Medical AIIntroducing PLIP, a foundation model for pathology — Introduction The ongoing AI revolution is bringing us innovations in all directions. OpenAI GPT(s) models are leading the development and showing how much foundation models can actually make some of our daily tasks easier. …Machine Learning10 min readMachine Learning10 min read
Published inTowards Data Science·Aug 8RecList 2.0: Open-Source Systematic Testing of ML ModelsA new RecList to provide more flexibility and better support for evaluation — Introduction Evaluation is a complex matter. It is often hard to manage the different components that are involved in writing evaluation pipelines, you have your model somewhere, you need to load it, then get the test, then run the tests, and so on and so forth. And then? well, you have…Recommender Systems7 min readRecommender Systems7 min read
Aug 11, 2022A Rounded Evaluation of Recommender SystemsEvalRS: Evaluating Recommender Systems on Many Tests — This article describes a novel data and code challenge that is currently running: EvalRS. We decided to organize EvalRS with friends from Coveo, Microsoft, and NVIDIA, to better understand evaluation in Recommender Systems. Anybody can join the challenge. There are prizes for best systems, best ideas and best student work…Machine Learning8 min readMachine Learning8 min read
Published inTowards Data Science·Feb 1, 2022How to Train your CLIPIntroduction to CLIP and to how we fine-tuned it for the Italian Language — During July, HuggingFace and Google organized a joint Community week in which interested people could make use of Google TPUs to experiment with projects they liked (by also using the JAX library).Machine Learning8 min readMachine Learning8 min read
Published inTowards Data Science·Oct 13, 2021Language Invariant Properties in Natural Language ProcessingAre text properties kept when you transform (e.g., translate) a message in another language? — When you transform a text (i.e., translate, paraphrase, summarize it), you expect the general properties of your message to not change from input to output. For example, you expect your message to be perceived as happy even when translated to another language. Issues can arise when this does not happen…Language6 min readLanguage6 min read
Oct 8, 2021MilaNLP 2021 in Review Part III: Reasoning, Meaning, and LanguageReviewing MilaNLP 2021 research papers on reasoning, meaning and language — In this blog post series, we revise what MilaNLP has been doing during 2021, analyzing the main themes of research and which output the team has produced. MilaNLP is the NLP Lab in Milano (Italy) lead by Prof. Dirk Hovy at Bocconi University. The first blog post covered what we…Machine Learning5 min readMachine Learning5 min read
Sep 28, 2021MilaNLP 2021 in Review Part II: Text AnalyticsReviewing MilaNLP 2021 research papers on text analytics — In this blog post series, we revise what MilaNLP has been doing during 2021, analyzing the main themes of research and which output the team has produced. MilaNLP is the NLP Lab in Milano (Italy) lead by Prof. Dirk Hovy at Bocconi University. The first blog post covered what we…Language8 min readLanguage8 min read
