The candidate will work on the project SLICE, which aims to develop and validate an authoring-friendly framework for the creation of transparent social intelligent agents capable of being deployed as virtual characters in training simulations or games or used to drive the behaviour of social robots. This framework joins two until now disparate areas of artificial intelligence research, namely, social agent architectures and machine learning. In particular, the candidate will work on the Model and Dialog System components.

Pain is a private and subjective experience, dependent on a complex cognitive process. These properties complicate the clinician's essential task of perceiving the patient's actual experience, given that it is only accessible from the outside through the lens of expressions and behaviors of pain. By modeling this experience through verbal reporting, it may be possible to better objectify the pain perceived by the patient, and thus provide a more adequate, personal treatment. This is motivated by the study of the cognitive process that embeds the painful experience, which determines, namely, that the emotional, psychosocial, and sociocultural dimensions of the subject in pain play a specific part in modulating the perception of pain and corresponding suffering and expression, and the study of the language of pain, which is shown to carry part of this information.
The primary objective of the present project is to evaluate the verbal description of the chronic pain experience of a restricted group of patients in order to develop a computational method to support clinical pain assessment. To this end, three main phases can be outlined, (1) data collection, (2) linguistic analysis, and (3) paralinguistic analysis.
The data collection phase aims at continuously collecting interviews with such patients, attending to the context in which the pain experience is being described, as it is shown to affect both the vocabulary and the way it is reported. Therefore, with respect to the primary objective, the data collection, consisting of an interview and a complementary form per patient, will take place in the medical office immediately after the medical appointment. The set of questions composing the interview is the result of a design process that aimed at obtaining a natural description of the patient’s pain experience, in their own words, but, at the same time, directing it towards the cognitive topics that have been identified as the most relevant for pain assessment. All data will be anonymized and the presentation of research results will never resort to individual references.
In the linguistic analysis phase, syntactic and semantic structures of textual descriptions of pain may yield correlations between the content of these descriptions and other relevant medical or non-medical aspects of the experience. This includes the identification of the most significant descriptors or qualifying attributes, the aggregation of descriptions focusing on the same or similar concepts, sentiment analysis, and regression of any value from a description. This analysis may be performed with a multitude of methods and models.
The paralinguistic analysis phase, methods to evaluate the patient’s verbalization of pain without explicitly considering the actual semantic or structural contents of the description. Thus, the speech signal can be processed and relevant information not present in the textual transcription can be extracted, which will allow to further characterize the patient and infer possible states.

The selected candidate will be a member of the research project PassCert, which aims at building an open-source, proof-of-concept password manager that through the use of formal verification, is guaranteed to satisfy properties on data storage and password generation. PassCert is a research collaboration between researchers from INESC-ID Lisboa (PT), INESC TEC (PT), and Carnegie Mellon University (US).
The selected candidate will:
1) Contribute to the collection of functional and security requirements for the proof-of-concept password manager and to the identification of properties that will be formally verified.
2) Formally verify properties relevant to password managers (e.g. properties on generation of secure passwords and properties related to data location).
3) Contribute to the development of the proof-of-concept verified password manager.
4) Actively participate in and contribute to PassCert's activities and regular meetings.

LAW-NLP aims to explore the use of natural language processing to help users understand and identify relevant Portuguese consumer laws that apply to their situation. To that end, the applicant will explore the automatic extraction of semantic information from texts in Portuguese Consumer Law.

D.O.T. is a four-year research program about strengthening connections between young people. We need good connections with our peers to stay healthy and happy.  D.O.T. will develop a unique new online platform and digital games that will help young people develop the skills they need to navigate their social environments. 
Online, individualized learning will be provided through a suite of digital experiences – innovative games and interactive media – enriched by real-time interaction with other young people in similar situations. The applicant will be responsible for the development of a collaborative visual novel where players have to make joint decisions on how to overcome problematic situations in a teenager's daily life.

BI| 2021/136
1) Explore using ML-based techniques, such as the newly proposed transformers (e.g., CodeBERT) to do automatic program repair.
2) Research, design, and development of a ML-based algorithm to do automatic program repair
3) Empirically evaluate and compare algorithm against state-of-the-art
4) Publish a research paper
BI| 2021/137
	1) Perform an extensive survey on techniques of testing, debugging, and repair quantum programs
	2) Develop a framework to do mutation testing and repair of quantum programs
	3) Empirically evaluate and compare algorithm against state-of-the-art
	4) Publish a research paper

The major research goals for this grant are the following:
1.	conduct a comprehensive exploratory analysis of medical emergencies in continental Portugal over the past few years, with particular focus on: (1) the distribution of the prevalence of emergencies by type and severity and (2) in the distribution of emergency response with a focus on service, dispatch and arrival times;
2.	discover discriminative patterns of emergency prevalence by region; 
3.	incorporate meteorological and calendar information in the discovery process;
4.	validate the discovered patterns according to their statistical significance, relevance and discriminative power;
5.	develop associative forecasting models based on the patterns discovered;
6.	extend the discovery of discriminative patterns to study the adequacy of emergency responses.

The general goal is to build humour skills in an AI agent to be learned by playing the game Cards Against Humanity. The work involves developing a digital version of the game Cards Against Humanity and develop and integrate a data base of cards with semantic tags. From the data collected with the game some machine learning techniques will be explored to learn a model of humor. The work will also be done in collaboration with a psychology team (from ISCTE) and a team from the US University, Carnegie Mellon University.

This grant is offered in the context of the European project EPEEC, "European joint Effort toward a Highly Productive Programming Environment for Heterogeneous". The main general objective of EPEEC is to develop and deploy a well-integrated, comprehensive parallel programming environment targeting exascale systems that turns next-generation supercomputers into manageable platforms for  domain application developers.
One focus of EPEEC is the rise of new types of byte-addressable persistent memory memories (PM), such as Intel’s Optane PM, which promise an exciting reality where tomorrow’s High Performance Computing (HPC) architectures will have hybrid memory architectures that combine each of these memories within the same physical address space. This enables applications to choose where to place their pages. For instance, the application may prefer map the pages containing performance-critical data structures to DRAM for superior performance, while other data structures may reside on PM. The goal of this grant is to study how the operating system, namely its virtual memory manager, can monitor virtual page usage and automatically map/migrate virtual pages to the most appropriate physical memory. A novel page mapper will be designed, implemented and evaluated under relevant HPC workloads.
The precise goals of the grant are: 
•	Continuing previous work already developed by our team in the context of EPEEC, optimize and extend its design to support advanced features such as: support for large pages, integration with profiling-based placement models, adaptive mechanisms.
•	Design, implement and evaluate the improved variant of the Current solution.
•	Produce a document describing the design, implementation and evaluation stages of the work, to be submitted to a top international scientific venue.

for more information please check
http://www.eracareers.pt/opportunities/index.aspx?task=global&jobId=132095

The DETECT project will research data mining and artificial intelligence techniques (e.g., classification of clinical notes and other unstructured data) to analyze, in a concerted manner, multiple data streams produced in real time, with the aim of informing epidemiological surveillance systems. Within the scope of a specific project task, INESC-ID aims to recruit one BI-M researcher to work on clinical natural language processing, addressing tasks such as extracting information (e.g., syndrome, symptom, procedural, and disease information) from textual descriptions present in electronic health records, in order to avoid delays and improve the granularity of manual coding. Candidates should preferably have previous experience in machine learning, deep learning approaches for natural language processing, and/or biomedical informatics.

The main objective of this scholarship is the integration of heterogeneous sources of spatiotemporal data, specifically:
1) design and implementation of relational and multidimensional schema for the identified data sources
2) external evaluation of spatiotemporal data mining algorithms
3) development of end-to-end application with potential access via Android

Development and evaluation of a system to optimize data placement in distributed data stores (such as Key Value Stores or relational databases) based on the symbolic execution of application's code. The symbolic execution method will be leveraged to extract in an automatic fashion the optimal placement of data, where optimality is defined based on the number of remote data accesses required to execute transactions as well as on the balance of data partitions in the system.
The project aims at automatically analyzing Java code using the Java Path Finder symbolic execution, in combination with the METIS graph partitioning tool and logical toolkits based on Mathematica.

Goal: to improve the performance of permissionless blockchains by extending (rather than replacing) their blockchain-based consensus foundation with hybrid consistency models that, whenever possible, avoid the use of consensus.
The solutions developed in the context of the grant should, hence, extend permissionless blockchains to offer two views, each with distinct consistency properties: a strongly-consistent red view and a weaker blue view. When an application submits a transaction to update the replicated data maintained by the blockchain, or when it reads from that state, the application specifies which view it wishes to access depending on how much consistency it needs. The red view is sequentially consistent and is implemented, at a considerable latency, by the original blockchain-based consensus protocol. The blue view, in turn, provides causal consistency, while also preventing censorship and double-spending anomalies. Since the blue view does not require consensus, its  latency should be orders of magnitude lower than the red view.
 
Plan: the work carried out during the grant should result in the design, implementation and evaluation of one or more solutions that meet the above goal. A research paper describing such results is to be prepared and submitted to a top international scientific venue.

for more information please check
http://www.eracareers.pt/opportunities/index.aspx?task=global&jobId=132094

1) Learn the internals of programming smart network equipment and catalog the requirements, constraints, and limitations of each platform. 2) Help build the first SyNAPSE research prototype synthesis engine. 3) Develop optimizations for the synthesis engine to offload functionality to the smart devices.

1) Learn the internals of programming smart network equipment and catalog the requirements, constraints, and limitations of each platform. 2) Help build the first SyNAPSE research prototype synthesis engine. 3) Develop optimizations for the synthesis engine to offload functionality to the smart devices.