arXiv research

Improved negation detection in Dutch clinical texts using machine learning.

Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials. This represents a rich source of information from which one can create value for people, organizations and businesses. For instance, recommender systems can benefit from automatically understanding…

Convolutional neural network improves assertion detection in multi-label clinical text.

Motivated by the need to automate medical information extraction from free-text radiological reports, we present a bi-directional long short-term memory (BiLSTM) neural network architecture for modelling radiological language. The model has been used to address two NLP tasks: medical named-entity recognition (NER) and …

QNNs can't distinguish binary signals from their negations, revealing a new symmetry.

Early detection of preventable diseases is important for better disease management, improved inter-ventions, and more efficient health-care resource allocation. Various machine learning approacheshave been developed to utilize information in Electronic Health Record (EHR) for this task. Majorityof previous attempts, ho…

This paper describes the resource- and system-building efforts of an eight-week Johns Hopkins University Human Language Technology Center of Excellence Summer Camp for Applied Language Exploration (SCALE-2009) on Semantically-Informed Machine Translation (SIMT). We describe a new modality/negation (MN) annotation schem…

Extracting and detecting spike activities from the fluorescence observations is an important step in understanding how neuron systems work. The main challenge lies in that the combination of the ambient noise with dynamic baseline fluctuation, often contaminates the observations, thereby deteriorating the reliability o…

Systematic review of ML models for detecting social media deception.

New method detects when models influence their own drift in real-time data streams.

One of the most pressing questions in climate science is that of the effect of anthropogenic aerosol on the Earth's energy balance. Aerosols provide the `seeds' on which cloud droplets form, and changes in the amount of aerosol available to a cloud can change its brightness and other physical properties such as optical…

Study shows some complex shapes don't fit a certain property.

Unified framework evaluates different nearest neighbor classification methods.

This study analyzes how RNNs process context in sentiment analysis.

It is a conjecture that the signature of a positive link is bounded below by an increasing function of its negated Euler characteristic. In relation to this conjecture, we apply the generator description for canonical genus to show that the boundedness of the genera of positive knots with given signature can be algorit…

Study how predictions affect the data they're based on, improving generalization guarantees.

The scientific data about the state of our planet, presented at the 2012 (Rio+20) summit, documented that today's human family lives even less sustainably than it did in 1992. The data indicate furthermore that the environmental impacts from our current economic activities are so large, that we are approaching situatio…

PolySwarm uses a swarm of LLMs to predict and arbitrage prediction markets.

Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the decision-making process. In this paper, we apply visualization techniques to observe h…

Efficient oblique RSF method improves prediction and interpretability.

Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mahé, a novel approach to provide Model-agnostic hierarchical éxplanations of how powerful machine learning models, such as deep ne…

We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose examples to label in such a way as to make the labeled set and the unlabeled pool …

Sensor fusion is a key technology that integrates various sensory inputs to allow for robust decision making in many applications such as autonomous driving and robot control. Deep neural networks have been adopted for sensor fusion in a body of recent studies. Among these, the so-called netgated architecture was propo…

Word vectors are at the core of many natural language processing tasks. Recently, there has been interest in post-processing word vectors to enrich their semantic information. In this paper, we introduce a novel word vector post-processing technique based on matrix conceptors (Jaeger2014), a family of regularized ident…

Coordinate descent methods usually minimize a cost function by updating a random decision variable (corresponding to one coordinate) at a time. Ideally, we would update the decision variable that yields the largest decrease in the cost function. However, finding this coordinate would require checking all of them, which…

The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents. In this work, we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms of the negation, disjunction and conjunction of a set of base tasks. We then sho…

In this paper we apply a compressibility loss that enables learning highly compressible neural network weights. The loss was previously proposed as a measure of negated sparsity of a signal, yet in this paper we show that minimizing this loss also enforces the non-zero parts of the signal to have very low entropy, thus…

Neuro-symbolic agent learns systematic generalisation from formal instructions.

We fully describe the horofunction boundary $\partial_h L_2$ with the word metric associated with the generating set $\{t,at\}$ (i.e the metric arising in the Diestel-Leader graph $\text{DL}(2,2)$). The visual boundary $\partial_\infty L_2$ with this metric is a subset of $\partial_h L_2$. Although $\partial_\infty L_2…

Sign equivariant networks improve model expressiveness for spectral geometric learning.

Enhances quantum machine learning models using Fock states.

UTE improves reinforcement learning by measuring action uncertainty, enhancing policy learning efficiency.

The driving force behind the recent success of LSTMs has been their ability to learn complex and non-linear relationships. Consequently, our inability to describe these relationships has led to LSTMs being characterized as black boxes. To this end, we introduce contextual decomposition (CD), an interpretation algorithm…

Active learning can't improve over passive in certain settings.

Recently, several methods have been proposed to explain the predictions of recurrent neural networks (RNNs), in particular of LSTMs. The goal of these methods is to understand the network's decisions by assigning to each input variable, e.g., a word, a relevance indicating to which extent it contributed to a particular…

Energy-based models can generate complex images by combining simpler concepts.

DVE uses GPs on DNN outputs to provide UQ without retraining.

Statistical model checking for PCTL on MDPs using reinforcement learning.

Let $\R$ be a real closed field, ${\mathcal Q} \subset \R[Y_1,...,Y_\ell,X_1,...,X_k],$ with $ °_{Y}(Q) \leq 2, °_{X}(Q) \leq d, Q \in {\mathcal Q}, #({\mathcal Q})=m$, and ${\mathcal P} \subset \R[X_1,...,X_k]$ with $°_{X}(P) \leq d, P \in {\mathcal P}, #({\mathcal P})=s$. Let $S \subset \R^{\ell+k}$ be a semi-alg…

Antithetic noise improves diffusion models' uncertainty quantification.

We prove a nearly optimal bound on the number of stable homotopy types occurring in a k-parameter semi-algebraic family of sets in $\R^\ell$, each defined in terms of m quadratic inequalities. Our bound is exponential in k and m, but polynomial in $\ell$. More precisely, we prove the following. Let $\R$ be a real close…

Let $\R$ be a real closed field, ${\mathcal Q} \subset \R[Y_1,...,Y_\ell,X_1,...,X_k],$ with $ °_{Y}(Q) \leq 2, °_{X}(Q) \leq d, Q \in {\mathcal Q}, #({\mathcal Q})=m,$ and ${\mathcal P} \subset \R[X_1,...,X_k]$ with $°_{X}(P) \leq d, P \in {\mathcal P}, #({\mathcal P})=s$, and $S \subset \R^{\ell+k}$ a semi-algebr…

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound polic…

Entropy asymmetry affects regularization in ERM, leading to biased solutions.

Poly-GNNs achieve similar performance regardless of depth, highlighting graph noise's dominance.

In the present work some generalizations of the Hawking singularity theorems in the context of $f(R)$ theories are presented. The assumptions are of these generalized theorems is that the matter fields satisfy the conditions $\bigg(T_{ij}-\frac{g_{ij}}{2} T\bigg)k^i k^j\geq 0$ for any generic unit time like field, that…

The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans. This task is, however, not one which a computer can perform by default. Identifying sentiments in an automated, algorithmic manner will be a useful capability for business and research in their search …

Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.