Search By Subject

Training of multi-class or multi-label classification machines are embarrassingly parallelizable via the one-vs.-rest approach. However, training of all-in-one multi-class learning machines such as multinomial logistic regression or all-in-one multi-...

In this talk, I will present Merged-Averaged Classifiers via Hashing (MACH) for K-classification with ultra-large values of K. Compared to traditional one-vs-all classifiers that require $O(Kd)$ memory and inference cost, MACH only need $O(dłogK)$ (d is ...

The AI methods are regaining a lot of attention in the areas of data analytics and decision support. Given the increasing amount of information and computational resources available, it is now possible for intelligent algorithms to learn from the data ...

Semantic annotation in the biomedical domain raises the problem of classifying texts with large-scale taxonomies, a problem sometimes referred to as extreme classification. In this presentation, we will give an overview of this problem and the main ...

This challenge focuses on the use of semantic representation methods to support Visual Question Answering: given a large image collection, find a set of images matching natural language queries. The task supports advancing the state-of-the-art in Visual ...

The growing maturity of Natural Language Processing (NLP) techniques and resources is dramatically changing the landscape of many application domains which are dependent on the analysis of unstructured data at scale. The finance domain, with its ...

In this paper, we present a neural network based framework for answering non-factoid questions. The framework consists of two main components: Answer Retriever and Answer Ranker. In the first component, we leverage off-the-shelf retrieval models (e.g. ...

In this paper, we describe our ensemble approach for sentiment and aspect predictions in the financial domain for a given text. This ensemble approach uses Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) with a ridge regression ...

Aspect based sentiment analysis aims to detect an aspect (i.e. features) in a given text and then perform sentiment analysis of the text with respect to that aspect. This paper aims to give a solution for the FiQA 2018 challenge subtask 1. We perform ...

The goal of question answering with financial data is selecting sentences as answers from the given documents for a question. The core of the task is computing the similarity score between the question and answer pairs. In this paper, we incorporate ...

Aspect-based financial sentiment analysis, which aims to classify the text instance into a pre-defined aspect class and predict the sentiment score for the mentioned target. In this paper, we propose a neural network model, Attention-based LSTM model ...

The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At ...

In public online discussion forums, the large user base and frequent posts can create challenges for recommending threads to users. Importantly, traditional recommender systems, based on collaborative filtering, are not capable of handlingnever-seen-...

Structured prediction, where outcomes have a precedence order, lies at the heart of machine learning for information retrieval, movie recommendation, product review prediction, and digital advertising. Ordinal ranking, in particular, assumes that the ...

The data gathered from smart cities can help citizens and city manager planners know where and when they should be aware of the repercussions regarding events happening in different parts of the city. Most of the smart city data analysis solutions are ...

The emergence of open information extraction as a tool for constructing and expanding knowledge graphs has aided the growth of temporal data, for instance, YAGO, NELL and Wikidata. While YAGO and Wikidata maintain the valid time of facts, NELL records ...

Clustering narrow-domain short texts, such as academic abstracts, is an extremely difficult clustering problem. Firstly, short texts lead to low frequency and sparseness of words, making clustering results highly unstable and inaccurate; Secondly, ...

Today's Web applications tend to reason about cyclic data (i.e. facts that re-occur periodically) on the client side. Although they can benefit from efficient incremental maintenance algorithms capable of handling frequent data updates, existing rule-...

What if we delegated so much to autonomous AI and intelligent machines that They passed a law that forbids humans to carry out a number of professions We conceive the plot of a new episode of Black Mirror to reflect on what might await us and how we can ...

We envisage a revolutionary change in the approach to spambot detection: instead of taking countermeasures only after having collected evidence of new spambot mischiefs, in a near future techniques will be able to anticipate the ever-evolving spammers.