The Priberam Machine Learning Lunch Seminars are a series of informal meetings which occur every two weeks at Instituto Superior Técnico, in Lisbon. It works as a discussion forum involving different research groups, from IST and elsewhere. Its participants are interested in areas such as (but not limited to): statistical machine learning, signal processing, pattern recognition, computer vision, natural language processing, computational biology, neural networks, control systems, reinforcement learning, or anything related (even if vaguely) with machine learning.

The seminars last for about one hour (including time for discussion and questions) and revolve around the general topic of Machine Learning. The speaker is a volunteer who decides the topic of his/her presentation. Past seminars have included presentations about state-of-the-art research, surveys and tutorials, practicing a conference talk, presenting a challenging problem and asking for help, and illustrating an interesting application of Machine Learning such as a prototype or finished product.

Presenters can have any background: undergrads, graduate students, academic researchers, company staff, etc. Anyone is welcome both to attend the seminar as well as to present it. Ocasionally we will have invited speakers. See below for a list of all seminars, including the speakers, titles and abstracts.

Note: The seminars are held at lunch-time, and include delicious free food.

Feel free to join our mailing list, where seminar topics are announced beforehand. You may also visit the mailing list webpage. Anyone can attend the seminars; no registration is necessary. If you would like to present something, please send us an email.

The seminars are usually held every other Tuesday, from 1 PM to 2 PM, at the IST campus in Alameda. This sometimes changes due to availability of the speakers, so check regularly!

Tuesday, July 18th 2017, 13h00 - 14h00

Luís Sarmento (Tonic App)

Going Neurotic With Neural Word Embeddings... again!

Anfiteatro do Complexo Interdisciplinar

Instituto Superior Técnico - Alameda


Word embeddings, such as Word2Vec or Glove, are vector representations that capture lexical-semantic properties of words. They constitute a practical way for transferring knowledge between two machine learning models, and they contribute to greatly reducing the learning time required for solving various NLP tasks. There is great practical interest in experimenting with different word embedding models. Neural-based models, due to their flexibility, are a great framework for that experimentation. However, that very same flexibility also brings many degrees of freedom to the experimentation, which end up becoming a challenge in itself. In this talk, we will present Syntagma, a python toolkit (still under development) that enables rapid experimentation of neural word embedding models. We will present preliminary results of experimenting with some of the hyper-parameters of a baseline word embedding model (similar to Word2Vec), and we will discuss the next steps for Syntagma.


Bio: Luís Sarmento holds a PhD in Computer Science from University of Porto (2010), with background in Electrical Engineering (Bs+MsC) and Artificial Intelligence (MsC). He has been working in the fields of Natural Language / Search for about 15 years, both as a member of research groups at the University of Porto and in the industry. In 2010 he joined Portugal Telecom / SAPO as tech lead for Big-Data and Recommender Systems, and in 2012 he joined Amazon where, until early 2017, he led research teams in the fields of Query Understanding and Voice Shopping. He is now CTO of Tonic App (, a startup developing productivity tools for medical doctors.

Eventbrite - Going Neurotic With Neural Word Embeddings... again!