Selene Baez Santamaria

Selene Baez Santamaria
Vrije Universiteit Amsterdam | VU · Department of Computer Science

Master of Science

About

17
Publications
1,276
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
30
Citations
Citations since 2017
16 Research Items
30 Citations
2017201820192020202120222023024681012
2017201820192020202120222023024681012
2017201820192020202120222023024681012
2017201820192020202120222023024681012
Introduction
I do research combining complementary Artificial Intelligence techniques (from Machine Learning to Knowledge Representation). My major area of interest is Natural Language Processing as a means for data ingestion to and enrichment of knowledge graphs.

Publications

Publications (17)
Preprint
Full-text available
We present a new method based on episodic Knowledge Graphs (eKGs) for evaluating (multimodal) conversational agents in open domains. This graph is generated by interpreting raw signals during conversation and is able to capture the accumulation of knowledge over time. We apply structural and semantic analysis of the resulting graphs and translate t...
Preprint
Full-text available
This paper describes our contributions to the Shared Task of the 9th Workshop on Argument Mining (2022). Our approach uses Large Language Models for the task of Argument Quality Prediction. We perform prompt engineering using GPT-3, and also investigate the training paradigms multi-task learning, contrastive learning, and intermediate-task training...
Preprint
Full-text available
The paper describes a flexible and modular platform to create multimodal interactive agents. The platform operates through an event-bus on which signals and interpretations are posted in a sequence in time. Different sensors and interpretation components can be integrated by defining their input and output as topics, which results in a logical work...
Preprint
Full-text available
Background: Access to medical care is strongly dependent on resource allocation, such as the geographical distribution of medical facilities. Nevertheless, this data is usually restricted to country official documentation, not available to the public. While some medical facilities' data is accessible as semantic resources on the Web, it is not cons...
Preprint
Full-text available
We present EMISSOR: a platform to capture multimodal interactions as recordings of episodic experiences with explicit referential interpretations that also yield an episodic Knowledge Graph (eKG). The platform stores streams of multiple modalities as parallel signals. Each signal is segmented and annotated independently with interpretation. Annotat...
Conference Paper
Query popularity is a main feature in web-search auto-completion. Several personalization features have been proposed to support specific users' searches, but often do not meet the privacy requirements of a medical environment (e.g. clinical trial search). Furthermore, in such specialized domains, the differences in user expertise and the domain-sp...
Conference Paper
Access to medical care is strongly dependent on resource allocation, for example, the geographical distribution of medical facilities. Yet, hospital data is usually restricted to country official documentation, not available to the public. Furthermore, medical facilities’ data that is accessible as semantic resources on the web is not consistent in...
Conference Paper
Language identification remains a challenge for short texts originating from social media. Moreover, domain-specific terminology, which is frequent in the medical domain, may not change cross-linguistically, making language identification even more difficult. We conducted language identification on four datasets, two of them with general language,...
Chapter
This paper presents a model of contextual awareness implemented for a social communicative robot Leolani. Our model starts from the assumption that robots and humans need to establish a common ground about the world they share. This is not trivial as robots make many errors and start with little knowledge. As such, the context in which communicatio...
Poster
Full-text available
People and robots make mistakes and should therefore recognize and communicate about their "imperfectness" when they collaborate. In previous work [3, 2], we described a female robot model Leolani(L) that supports open-domain learning through natural language communication, having a drive to learn new information and build social relationships. The...
Conference Paper
We describe a model for a robot that learns about the world and her companions through natural language communication. The model supports open-domain learning, where the robot has a drive to learn about new concepts, new friends, and new properties of friends and concept instances. The robot tries to fill gaps, resolve uncertainties and resolve con...
Conference Paper
This paper describes the system that team MYTOMORROWS-TU DELFT developed for the 2019 Social Media Mining for Health Applications (SMM4H) Shared Task 3, for the end-to-end normalization of ADR tweet mentions to their corresponding MEDDRA codes. For the first two steps, we reuse a state-of-the art approach, focusing our contribution on the final ent...
Chapter
Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper ro...
Preprint
Full-text available
Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper ro...
Article
Full-text available
This paper presents a novel method for mining the individual travel behavior regularity of different public transport passengers through constructing travel behavior graph based model. The individual travel behavior graph is developed to represent spatial positions, time distributions, and travel routes and further forecasts the public transport pa...
Article
Full-text available
The goal of this project is to predict the opponent's configuration in a RoboCup SSL environment. For simplicity, a Markov model assumption is made such that the predicted formation of the opponent team only depends on its current formation. The field is divided into a grid and a robot state per player is created with information about its position...

Network

Cited By

Projects

Projects (2)
Project
The Spinoza-project Understanding-Language-By-Machines has funded a follow-up project “Make Robots talk and think” (2020-2024) for work on our robot project Leolani. Leolani uses communication to learn about us and the world but she also needs to learn our language at the same time. Communicating and reasoning over the physical world and the people she encounters is a real challenge.
Project
When a patient is seeking alternate treatment options, it is difficult to narrow down the most relevant trials or programs available from official registries. Current practice requires a keyword search of databases to find what they are looking for, which may require the user to know specific medical terms and inclusion/exclusion criteria. Our research goal is to leverage the use of NLP to extract relevant information from medical documents to automatically return the most relevant trials for individual patients.