Search

In the last decade, the major private IT companies have developed lots of cloud platforms for Natural Language Understanding (NLU), that are widely used for research and commercial purposes. One of the main reasons for the success of NLU platforms is because they allow to simplify the Chatbots or Spoken Dialogue Systems (SDS) development and, in many cases, without knowledge about programming languages. In this paper, we present a general description and a taxonomy that brings together features and constraints of different cloud-based NLU services available on the market. Furthermore, we provide an evaluation and a comparison concerning the ability to recognise the underlying intents of different sentences. The sentences used are a collection of requests made by users in Italian on an e-learning platform. This analysis wants to help the company, owner of the e-learning platform, to understand in which NLU platform it is better to build a chatbot for the Italian language aiming at answering the most frequently asked questions.

Accurate streamflow prediction is a fundamental task for integrated water resources management and flood risk mitigation. The purpose of this study is to forecast the water inflow to lake Como, (Italy) using different machine learning algorithms. The forecast is done for different days ranging from one day to three days. These models are evaluated by three statistical measures including Mean Absolute Error, Root Mean Squared Error, and the Nash-Sutcliffe Efficiency Coefficient. The experimental results show that Neural Network performs better for streamflow estimation with MAE and RMSE followed by Support Vector Regression and Random Forest.

A Multi-task model (MTM) learns specific features using shared and task specific layers among different tasks, an approach that turned out to be effective in those tasks where limited data is available to train the model. In this research, we utilize this characteristic of MTM using knowledge distillation to enhance the performance of a single task model (STM). STMs have difficulties in learning complex feature representations from a limited amount of annotated data. Distilling knowledge from MTM will help STM to learn more complex feature representations during the training phase. We use feature representations from different layers of a MTM to teach the student model during its training. Our approach shows distinguishable improvements in terms of F1-score with respect to STM. We further performed a statistical analysis to investigate the effect of different teacher models on different student models. We found that a Softmax-based teacher model is more effective for token level knowledge distillation than a CRF-based teacher model.

Automated planning is one of the most prominent AI challenges. In the last few decades, there has been a great deal of activity in designing planning techniques and planning engines, with a focus on forward state-space search. Despite the ubiquitous use of heuristics in AI planning, these techniques are susceptible to being easily trapped by undetected dead ends and huge search plateaus. In this paper we introduce a highly configurable heuristic adaptation process based on the idea of dynamically penalising unpromising actions when an inconsistency in the heuristic evaluation is detected; its aim is to reduce the bias affecting specific actions, thereby encouraging exploration by the search process and adding diversity in the neighbourhood selection process. Our extensive experimental analysis demonstrates that the proposed heuristic can be configured to improve significantly the performance of best first search planning on a range of benchmark domains.

Multi-task learning approaches have shown significant improvements in different fields by training different related tasks simultaneously. The multi-task model learns common features among different tasks where they share some layers. However, it is observed that the multi-task learning approach can suffer performance degradation with respect to single task learning in some of the natural language processing tasks, specifically in sequence labelling problems. To tackle this limitation we formulate a simple but effective approach that combines multi-task learning with transfer learning. We use a simple model that comprises of bidirectional long-short term memory and conditional random field. With this simple model, we are able to achieve better F1-score compared to our single task and the multi-task models as well as state-of-the-art multi-task models.

Radiological reports are a valuable source of textual information, which can be exploited to improve clinical care and to support research. Such information can be extracted and put into a structured form using machine learning techniques. Some of them rely not only on the classification labels but also on the manual annotation of relevant snippets, which is a time consuming job and requires domain experts. In this paper, we apply deep learning techniques and in particular Long Short Term Memory (LSTM) networks to perform such a task relying only on the classification labels. We focus on the classification of chest computed tomography reports in Italian according to a classification schema proposed for this task by the radiologists of Spedali Civili di Brescia. Each report is classified according to such schema using a combination of neural network classifiers. The resulting system is a novel classification system, which we compare to a previous system based on standard machine learning techniques which used annotations of relevant snippets.

Discovering the effect of the simultaneous assumption of drugs is a very important field in medical research that could improve the effectiveness of healthcare and avoid adverse drug reactions which can cause health problems to patients. Although there are several pharmacological databases containing information on drugs, this type of information is often expressed in the form of free text. Analyzing sentences in order to extract drug-drug interactions was the objective of the DDIExtraction-2013 task. Despite the fact that the challenge took place six years ago, the interest on this task is still active and several new methods based on Recurrent Neural Networks and Attention Mechanisms have been designed. In this paper, we propose a model that combines bidirectional Long Short Term Memory (LSTM) networks with the Self-Interaction Attention Mechanism. Experimental analysis shows how this model improves the classification accuracy reducing the tendency to predict the majority class resulting in false negatives, over several input configurations.

Biomedical named entity recognition (BioNER) is the task of categorizing biomedical entities. Due to the specific characteristics of the names of biomedical entities, such as ambiguity among different concepts or different ways of referring to the same entity, the BioNER task is usually considered more challenging compared to standard named entity recognition tasks. Recent techniques based on deep learning not only significantly reduce the hand crafted feature engineering phase but also determined relevant improvements in the BioNER task. However, such systems are still facing challenges. One of them is the limited availability of annotated text data. Multi-task learning approaches tackle this problem by training different related tasks simultaneously. This enables multi-task models to learn common features among different tasks where they share some layers. To explore the advantages of the multi-task learning, we propose a model based on convolution neural networks, long-short term memories, and conditional random fields. The model we propose shows comparable results to state-of-the-art approaches. Moreover, we present an empirical analysis considering the impact of different word input representations (word embedding, character embedding, and case embedding) on the model performance.

Partial Discharge (PD) pattern analysis is widely used for condition assessment of generator stator winding insulation. The common PD sources of generator stator winding are slot discharge, end winding surface discharge, discharge at void in bulk insulation and discharge due to delamination on conductor surface and machine learning techniques are commonly used to discriminate them. This paper presents a comparison of different machine learning techniques to classify 352 Phase Resolved PD (PRPD) patterns obtained from a 37.5 MW, 12.5 kV generator. Ninety-six features representing each PRPD pattern were considered in this analysis. Based on the analysis, PRPD patterns were classified into different types of internal discharges. Nine different supervised machine learning algorithms under four different techniques i.e. functional based techniques, probabilistic techniques, decision tree models and nearest neighbor search were used. For the training process 70% of PRPD patterns were used whereas the remaining samples were used for the testing of the trained models. It was found that the accuracy is above 95% for most of the tested algorithms. It can be concluded that PDs in generator stator insulation can effectively be assessed by PD pattern classification through supervised machine learning techniques.

In this paper we describe and analyze a new user interface program that allows students of nursery and primary schools to use digital microscopes in the Linux environment. Moreover, we want to provide teachers with new ideas for a conscious and effective use of digital microscopes in order to promote the interest toward the scientific exploration of nature in children.In our classes we have used the Intel® Play™ QX3™ Microscope, which is a unique tool to introduce children to technology. This microscope has technical features that make it very effective and simple to use; furthermore it allows, in combination with our software, to observe very small objects directly from the computer screen and realize videos by capturing images in long term experiments.Children can recombine the microscope images so as to produce new graphic objects, modify these images in a creative way and create new multimedia collections of their experiments. In particular, we aim at establishing a link among practical experience, geometry and artistic education; moreover, this tool can facilitate the integration of certified students, hyperactive students and students with deficit and attention disorder, since it can promote their concentration through an operative approach.

International audience; Radiological reporting generates a large amount of free-text clinical narratives, a potentially valuable source ofinformation for improving clinical care and supporting research. The use of automatic techniques to analyzesuch reports is necessary to make their content effectively available to radiologists in an aggregated form. In thispaper we focus on the classification of chest computed tomography reports according to a classification schemaproposed for this task by radiologists of the Italian hospital ASST Spedali Civili di Brescia. The proposed system isbuilt exploiting a training data set containing reports annotated by radiologists. Each report is classified accordingto the schema developed by radiologists and textual evidences are marked in the report. The annotationsare then used to train different machine learning based classifiers. We present in this paper a method based on acascade of classifiers which make use of a set of syntactic and semantic features. The resulting system is a novelhierarchical classification system for the given task, that we have experimentally evaluated.

Current work in planning with preferences assumes that user preferences are completely specified, and aims to search for a single solution plan to satisfy these. In many real world planning scenarios, however, the user may provide no knowledge or at best partial knowledge of her preferences with respect to a desired plan. In such situations, rather than presenting a single plan as the solution, the planner must instead provide a set of plans containing one or more plans that are similar to the one that the user really prefers. In this paper, we first propose the usage of different measures to capture the quality of such plan sets. These are domain-independent distance measures based on plan elements (such as actions, states, or causal links) if no knowledge of the user preferences is given, or the Integrated Convex Preference (ICP) measure in case incomplete knowledge of such preferences is provided. We then investigate various heuristic approaches to generate sets of plans in accordance with these measures, and present empirical results that demonstrate the promise of our methods.

Case-based planning (CBP) is an approach to planning where previous planning experience stored in a case base provides guidance to solving new problems. Such a guidance can be extremely useful when the new problem is very hard to solve, or the stored previous experience is highly valuable (because, e.g. it was provided and/or validated by human experts) and the system should try to reuse it as much as possible. In this work, we address CBP in PDDL domains with real-valued fluents, action durations and timed-initial literals, which are essential to model real-world planning problems involving continuous resources and temporal constraints. We propose some new heuristic techniques for retrieving a plan from a library of existing plans that is promising for solving a new planning problem encountered by the CBP system, i.e. that can be efficiently adapted to solve the new problem. The effectiveness of these techniques, which derive much of their power from the proposed use of the numerical/temporal information...