Spain

Presentation is about our chatbot creation platform and its dialog management techniques. The framework enables creating chatbots without coding using intent-slot model. It contains intent detection and dialog act classifier modules to understand user utterances more accurately. Also the framework includes and analytics tool to monitor and cluster past conversation data to discover topics and training sentences.

ECAI 2020

Domain-Independent, Task-Oriented Chatbot Creation and Conversation Policy Management Framework

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

"Static word embeddings, like word2vec or GloVe, are often assessed when solving syntactic and semantic analogies. Among the latter, we are interested in relations that one would find in lexical-semantic knowledge bases like WordNet, also covered in analogy test sets for English. This paper describes the creation of a new test for assessing Portuguese word embeddings, dubbed TALES, with an exclusive focus on lexical-semantic relations, acquired from lexical resources in Portuguese.
It further reports on the performance of methods previously used for solving analogies, with pre-trained Portuguese word embeddings, when applied to the created dataset, an experiment that revealed that TALES is challenging to solve.
Results achieved are briefly discussed, with conclusions that may be useful for developing new approaches for this problem, possibly new embeddings, as well as future versions of TALES."

 TALES: Test Set of Portuguese Lexical-Semantic Relations for Assessing Word Embeddings

"In this presentation we will show the application of the Thematic Theory and the Thematic Progression Theory to automatically annotate discourse features, which enable the inference of the implicit conceptual schemas of texts.
"

A new approach for extracting the conceptual schema of texts based on the linguistic Thematic Progression theory

Open information extraction (OpenIE) is a task of extracting structured information from unstructured texts independently of the domain. Recent advances have applied Deep Learning for Natural Language tasks improving the state-of-the-art, even though those methods usually require a large and high-quality corpus. The construction of an OpenIE dataset is a tedious and error-prone task, and one technique employed concerns the extractions from rule-based techniques and manual validation of those extraction triples. As low-resource languages usually lack available datasets for the application of high-performance Deep Learning techniques, our intuition is that a low-resource model based-on multilingual information can learn generalizations across languages and benefits from cross-lingual data. Moreover, we would like to interpret the set of generalized information gathered from multilingual learning to increase the Open IE classification task. In this paper, we introduce TabOIEC, a multilingual classifier based on generic morpho-syntactic features. Our classifier carries a glass-box method which can provide interpretation about some of the classifier decisions. We evaluate our approach through a small corpus of Open IE extractions for the English, Spanish, and Portuguese languages. Our results consider that for all languages our approach improves F1 measures, particularly for monolinguality. Experiments on Zero-shot learning provide evidence that our TabOIEC generalizes the classifier on other languages than that trained, although there is a shy transfer learning among them. Experiments on multilinguality do reduce the cost of training, however, in our experiments were difficult to provide appropriate generalizations. 

Explainable Open IE Classifier with Morpho-syntactic Rules

Maintaining blood glucose in a target range is essential for people living with Type 1 diabetes in order to avoid excessive periods in hypoglycemia and hyperglycemia which can result in severe complications. Accurate blood glucose prediction can reduce this risk and enhance early interventions to improve diabetes management. However, due to the complex nature of glucose metabolism and the various lifestyle related factors which can disrupt this, diabetes management still remains challenging. In this work we propose a novel deep learning model to predict future BG levels based on the historical continuous glucose monitoring measurements, meal ingestion, and insulin delivery. We adopt a modified architecture of the generative adversarial network that comprises of a generator and a discriminator. The generator computes the BG predictions by a recurrent neural network with gated recurrent units, and the auxiliary discriminator employs a one-dimensional convolutional neural network to distinguish between the predictive and real BG values. Two modules are trained in an adversarial process with a combination of loss. The experiments were conducted using the OhioT1DM dataset that contains the data of six T1D contributors over 40 days. The proposed algorithm achieves an average root mean square error (RMSE) of 18.34 ± 0.17 mg/dL with a mean absolute error (MAE) of 13.37 ± 0.18 mg/dL for the 30-minute prediction horizon (PH) and an average RMSE of 32.31 ± 0.46 mg/dL with a MAE of 24.20 ± 0.42 for the 60-minute PH. The results are compared for clinical relevance using the Clarke error grid which confirms the promising performance of the proposed model.

Blood Glucose Prediction for Type 1 Diabetes Using Generative Adversarial Networks

We developed a system for predicting the prognosis for more than 2000 COVID-19 patients hospitalised at ASST Spedali Civili di Brescia, one of the hospitals with more COVID-19 patients in Italy. Our system is based on lab tests and X-Ray data and focuses on death risk at different times during the hospitalisation using randomized ensemble of decision trees.

Prognosis Prediction in Covid-19 Patients from Lab Tests and X-ray Data through Randomized Decision Trees

The use of artificial pancreas systems is becoming increasingly popular amongst patients with type 1 diabetes due to its effective ability to allow the patient better control of patient's own blood glucose levels compared to other more standard treatments. But what if the glucose monitor stops transmitting for an unpredictable period of time while the pump is still working? How should the pump react to guarantee the safety of the patients? In this presentation, we will discuss some potential failure mode strategies that we have explored and their corresponding results.

In Silico Comparison of Continuous Glucose Monitor Failure Mode Strategies for an Artificial Pancreas

Individuals with Type I diabetes (T1D) must frequently monitor their blood glucose (BG) and deliver insulin to regulate it. New devices like continuous glucose monitors (CGMs) and insulin pumps  have  helped  reduce  this  burden  by  facilitating  closed-loop technologies like the artificial pancreas (AP) for delivering insulin automatically. As more people use AP systems, which rely on a CGM and insulin pump, there has been a dramatic increase in the availability of large scale patient-generated health data (PGHD) in T1D. This data can potentially be used to train robust, generalizable models for accurate BG forecasting which can then be used to make forecasts for smaller datasets like OhioT1DM in real-time. In this work, we investigate the potential and pitfalls of using knowledge distillation to transfer knowledge from a model learned from one dataset to another and compare it with the baseline case of using either dataset alone. We  show  that  using  a  pre-trained  model  to  do  BG  forecasting  for OhioT1DM from CGM data only (univariate setting) has comparable performance to training on OhioT1DM itself. Using a single-step, univariate  recurrent  neural  network  (RNN)  trained  on  OhioT1DM data alone, we achieve an overall RMSE of 19.21 and 31.77 mg/dl for a prediction horizon (PH) of 30 and 60 minutes respectively

Investigating potentials and pitfalls of knowledge distillation across datasets for blood glucose forecasting

In this position paper, we highlight that being able to analyse the cause-effect relationships for determining the causal status among a set of events is an essential requirement in many contexts and argue that cannot be overlooked when building systems targeting real-world use cases. This is especially true for medical contexts where the understanding of the cause(s) of a symptom, or observation, is of vital importance. However, most approaches purely based on Machine Learning (ML) do not explicitly represent and reason with causal relations, and may therefore mistake correlation for causation. In the paper, we therefore argue for an approach to extract causal relations from text, and represent them in the form of Knowledge Graphs (KG), to empower downstream ML applications, or AI systems in general, with the ability to distinguish correlation from causation and reason with causality in an explicit manner. So far, the bottlenecks in KG creation have been scalability and accuracy of automated methods, hence, we argue that two novel features are required from methods for addressing these challenges, i.e. (i) the use of Knowledge Patterns to guide the KG generation process towards a certain resulting knowledge structure, and (ii) the use of a semantic referee to automatically curate the extracted knowledge. We claim that this will be an important step forward for supporting interpretable AI systems, and integrating ML and knowledge representation approaches, such as KGs, which should also generalise well to other types of relations, apart from causality.

Towards Causal Knowledge Graphs - Position Paper

In this presentation, we quantify the uncertainty of deep neural networks (DNNs) for the task of Chest X-Ray (CXR) image classification. We investigate uncertainties of several commonly used DNN architectures including ResNet, ResNeXt, DenseNet and SENet. We propose an uncertainty based strategy and analyze the impact of this strategy on the classifier performance. Results show that utilizing uncertainty information may improve DNN performance for some metrics and observations.

Downloads

Next from ECAI 2020

TALES: Test Set of Portuguese Lexical-Semantic Relations for Assessing Word Embeddings

Similar lecture

Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ECAI 2020

TALES: Test Set of Portuguese Lexical-Semantic Relations for Assessing Word Embeddings

Similar lecture

Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems

Downloads