Archive

Understanding how people who commit suicide perceive their cognitive states and emotions represents a crucially open scientific challenge. We build upon cognitive network science, psycholinguistics, and semantic frame theory to introduce a network representation of suicidal ideation as expressed in multiple suicide notes. By reconstructing the knowledge structure of such notes, we reveal interconnections between the semantic ideas and emotional states of people who committed...

Cleverly is an end-to-end AI layer for customer service platforms that provides intelligent automation and efficiency and unlike others is easy to use. We reduce the effort agents spend on repetitive tasks and searching for the right information, giving them more time to focus on the complex queries. In this talk, we will show how Cleverly tackles Customer Service productivity issues. Then, we will focus...

Misinformation is considered one of the major challenges of our times resulting in numerous efforts against it. Fact-checking, the task of assessing whether a claim is true or false, is considered a key weapon in reducing its impact. In the first part of this talk, Professor Andreas Vlachos will present his recent and ongoing work on automating this task using natural language processing, moving beyond...

Visual attention mechanisms have become an important component of neural network models for Computer Vision applications, allowing them to attend to finite sets of objects or regions and identify relevant features. A key component of attention mechanisms is the differentiable transformation that maps scores representing the importance of each feature into probabilities. The usual choice is the softmax transformation, whose output is strictly dense, assigning...

Machine learning has been used to aid decision-making in several domains, from healthcare to finance. Understanding the decision process of ML models is paramount in high-stakes decisions that impact people's lives, otherwise, loss of control and lack of trust may arise. Often, these decisions have a sequential nature. For instance, the transaction history of a credit card must be considered when predicting the risk of...

Spoken Language Understanding consists in extracting semantic information conveyed by speech signal in order to project it into a representation manageable by a software application. This research topic encompasses several tasks like domain classification, named entity recognition, slot filling… By some aspects, it is also very close to machine translation. SLU has been encouraged by NIST effort during the 90’s and during the last three...

This work introduces TrimTuner - the first system for optimizing machine learning jobs in the cloud by exploiting sub-sampling techniques to reduce the cost of the optimization process, while keeping into account user-specified constraints. TrimTuner jointly optimizes the cloud and application-specific parameters and, unlike state of the art works for cloud optimization, eschews the need to train the model with the full training set every...