INESC-ID

About: INESC-ID is a nonprofit organization based out in Lisbon, Portugal. It is known for research contribution in the topics: Computer science & Context (language use). The organization has 932 authors who have published 2618 publications receiving 37658 citations.

Automated anonymization of text documents

Abstract: Sharing data in the form of text is important for a wide range of activities but it also raises a concern about privacy when sharing data that could be sensitive. Automated text anonymization is a solution for removing all the sensitive information from documents. However, this is a challenging task due to the unstructured form of textual data and the ambiguity of natural language. In this work, we present our implementation of an automated anonymization system, built in a modular structure, for documents written in Portuguese. Four different methods of anonymization are evaluated and compared. Two methods replace the sensitive information by artificial labels: suppression and tagging. The other two methods replace the information by textual expressions: random substitution and generalization. Evaluation showed that the use of the tagging and the generalization methods facilitates the reading of an anonymized text while preventing some semantic drifts caused by the remotion of the original information.

The INESC-ID Multi-Modal System for the ADReSS 2020 Challenge

Abstract: This paper describes a multi-modal approach for the automatic detection of Alzheimer's disease proposed in the context of the INESC-ID Human Language Technology Laboratory participation in the ADReSS 2020 challenge. Our classification framework takes advantage of both acoustic and textual feature embeddings, which are extracted independently and later combined. Speech signals are encoded into acoustic features using DNN speaker embeddings extracted from pre-trained models. For textual input, contextual embedding vectors are first extracted using an English Bert model and then used either to directly compute sentence embeddings or to feed a bidirectional LSTM-RNNs with attention. Finally, an SVM classifier with linear kernel is used for the individual evaluation of the three systems. Our best system, based on the combination of linguistic and acoustic information, attained a classification accuracy of 81.25%. Results have shown the importance of linguistic features in the classification of Alzheimer's Disease, which outperforms the acoustic ones in terms of accuracy. Early stage features fusion did not provide additional improvements, confirming that the discriminant ability conveyed by speech in this case is smooth out by linguistic data.

A comparative study of interaction metaphors for large-scale displays

Abstract: Large-scale displays require new interaction techniques because of their physical size. There are technologies that tackle the problem of interaction with such devices by providing natural interaction to larger surfaces. We argue, however, that large-scale displays offer physical freedom that is not yet being applied to interaction. To better understand how distance affects user interaction, we present a comparative study of interaction metaphors for large-scale displays. We present three metaphors: Grab, Point and Mouse. The metaphors were included in our tests as we felt that each would be more suited to a specific distance: this is the focus of our tests. We then asked the users to solve a puzzle using those metaphors from different distances. We discovered that the point metaphor achieves better results on all tests. However, there is evidence that grab and mouse remain valid for specific tasks.

Adaptive motion estimation processor for autonomous video devices

Abstract: Motion estimation is the most demanding operation of a video encoder, corresponding to at least 80% of the overall computational cost. As a consequence, with the proliferation of autonomous and portable handheld devices that support digital video coding, data-adaptive motion estimation algorithms have been required to dynamically configure the search pattern not only to avoid unnecessary computations and memory accesses but also to save energy. This paper proposes an application-specific instruction set processor (ASIP) to implement data-adaptive motion estimation algorithms that is characterized by a specialized datapath and a minimum and optimized instruction set. Due to its low-power nature, this architecture is highly suitable to develop motion estimators for portable, mobile, and battery-supplied devices. Based on the proposed architecture and the considered adaptive algorithms, several motion estimators were synthesized both for a Virtex-II Pro XC2VP30 FPGA from Xilinx, integrated within an ML310 development platform, and using a StdCell library based on a 0.18 µm CMOS process. Experimental results show that the proposed architecture is able to estimate motion vectors in real time for QCIF and CIF video sequences with a very low-power consumption. Moreover, it is also able to adapt the operation to the available energy level in runtime. By adjusting the search pattern and setting up a more convenient operating frequency, it can change the power consumption in the interval between 1.6mW and 15 mW.

A Multilevel Fault-Tolerant Power Converter for a Switched Reluctance Machine Drive

Abstract: Reliability in the electrical drives is becoming an important issue in many applications. In this context, the reliability associated to the switched reluctance machine ( SRM ) is also an important area of research. One of the major problems, that strongly affect its operation, are drive power semiconductors faults. Typical power converter topologies used in SRM drives cannot handle faults in their power semiconductors. So, this paper presents a power converter topology that provides fault-tolerant capabilities to the drive under a switch fault. This power converter will be used considering that a change in the direction of the current that flows in the SRM windings does not affect the behavior of the machine. Besides that, the proposed power converter will allow to generate multilevel phase voltages in order to apply different voltage levels as function of the SRM speed. A laboratory power converter was developed to test the SRM drive in normal and faulty conditions. From the obtained results it was possible to verify the fault-tolerant capability of the drive under switch faults in different devices and failure modes. It was also possible to confirm the multilevel operation of the drive.