arXiv subjects

Ross Sparks

Publications and source records attributed to Ross Sparks.

11 recordsLinked to original sources

arXiv2020

DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains

We address the issue of having a limited number of annotations for stance classification in a new domain, by adapting out-of-domain classifiers with domain adaptation. Existing approaches often align different domains in a single, global feature space (or view), which may fail to fully capture the richness of the languages used for expressing stances, leading to reduced adaptability on stance data. In this paper, we identify two major types of stance expressions that are linguistically distinct, and we propose a tailored dual-view adaptation network (DAN) to adapt these expressions across domains. The proposed model first learns a separate view for domain transfer in each expression channel and then selects the best adapted parts of both views for optimal transfer. We find that the learned view features can be more easily aligned and more stance-discriminative in either or both views, leading to more transferable overall features after combining the views. Results from extensive experiments show that our method can enhance the state-of-the-art single-view methods in matching stance data across different domains, and that it consistently improves those methods on various adaptation tasks.

cs.CL↗

arXiv2019

Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection

Personal health mention detection deals with predicting whether or not a given sentence is a report of a health condition. Past work mentions errors in this prediction when symptom words, i.e. names of symptoms of interest, are used in a figurative sense. Therefore, we combine a state-of-the-art figurative usage detection with CNN-based personal health mention detection. To do so, we present two methods: a pipeline-based approach and a feature augmentation-based approach. The introduction of figurative usage detection results in an average improvement of 2.21% F-score of personal health mention detection, in the case of the feature augmentation-based approach. This paper demonstrates the promise of using figurative usage detection to improve personal health mention detection.

cs.CL↗

arXiv2019

A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics

Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better than Word2Vec, GloVe and the two adapted using the MESH ontology. There is an improvement of 2-4% in the accuracy when these context-based representations are used instead of word-based representations.

cs.CL↗

arXiv2019

Recognising Agreement and Disagreement between Stances with Reason Comparing Networks

We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods focus mainly on conversational settings, where dialogic features are used for (dis)agreement inference. We extend this scope and seek to detect stance (dis)agreement in a broader setting, where independent stance-bearing utterances, which prevail in many stance corpora and real-world scenarios, are compared. To cope with such non-dialogic utterances, we find that the reasons uttered to back up a specific stance can help predict stance (dis)agreements. We propose a reason comparing network (RCN) to leverage reason information for stance comparison. Empirical results on a well-known stance corpus show that our method can discover useful reason information, enabling it to outperform several baselines in stance (dis)agreement detection.

cs.CL↗

arXiv2019

Survey of Text-based Epidemic Intelligence: A Computational Linguistic Perspective

Epidemic intelligence deals with the detection of disease outbreaks using formal (such as hospital records) and informal sources (such as user-generated text on the web) of information. In this survey, we discuss approaches for epidemic intelligence that use textual datasets, referring to it as `text-based epidemic intelligence'. We view past work in terms of two broad categories: health mention classification (selecting relevant text from a large volume) and health event detection (predicting epidemic events from a collection of relevant text). The focus of our discussion is the underlying computational linguistic techniques in the two categories. The survey also provides details of the state-of-the-art in annotation techniques, resources and evaluation strategies for epidemic intelligence.

cs.CL↗

arXiv2018

Cross-Target Stance Classification with Self-Attention Networks

In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually trained for prediction on the same target. In this work, we explore the potential for generalizing classifiers between different targets, and propose a neural model that can apply what has been learned from a source target to a destination target. We show that our model can find useful information shared between relevant targets which improves generalization in certain scenarios.

cs.CL↗

arXiv2016

Monitoring communication outbreaks among an unknown team of actors in dynamic networks

This paper investigates the detection of communication outbreaks among a small team of actors in time-varying networks. We propose monitoring plans for known and unknown teams based on generalizations of the exponentially weighted moving average (EWMA) statistic. For unknown teams, we propose an efficient neighborhood-based search to estimate a collection of candidate teams. This procedure dramatically reduces the computational complexity of an exhaustive search. Our procedure consists of two steps: communication counts between actors are first smoothed using a multivariate EWMA strategy. Densely connected teams are identified as candidates using a neighborhood search approach. These candidate teams are then monitored using a surveillance plan derived from a generalized EWMA statistic. Monitoring plans are established for collaborative teams, teams with a dominant leader, as well as for global outbreaks. We consider weighted heterogeneous dynamic networks, where the expected communication count between each pair of actors is potentially different across pairs and time, as well as homogeneous networks, where the expected communication count is constant across time and actors. Our monitoring plans are evaluated on a test bed of simulated networks as well as on the U.S. Senate co-voting network, which models the Senate voting patterns from 1857 to 2015. Our analysis suggests that our surveillance strategies can efficiently detect relevant and significant changes in dynamic networks.

stat.ME↗

arXiv2016

An overview and perspective on social network monitoring

In this expository paper we give an overview of some statistical methods for the monitoring of social networks. We discuss the advantages and limitations of various methods as well as some relevant issues. One of our primary contributions is to give the relationships between network monitoring methods and monitoring methods in engineering statistics and public health surveillance. We encourage researchers in the industrial process monitoring area to work on developing and comparing the performance of social network monitoring methods. We also discuss some of the issues in social network monitoring and give a number of research ideas.

stat.OT↗

arXiv2015

Modelling Hospital length of stay using convolutive mixtures distributions

Length of hospital stay (LOS) is an important indicator of the hospital activity and management of health care. The skewness in the distribution of LOS poses problems in statistical modelling because it fails to adequately follow the usual traditional distribution such as the log-normal distribution. The aim of this work is to model the variable LOS using the convolution of two distributions; a technique well known in the signal processing community. The specificity of that model is that the variable of interest is considered to be the resulting sum of two random variables with different distributions. One of the variables will feature the patient-related factors in terms their need to recover from their admission condition, while the other models the hospital management process such as the discharging process. Two estimation procedures are proposed. One is the classical maximum likelihood, while the other relates to the expectation maximisation algorithm. We will present some results obtained by applying this model to a set of real data from a group of hospitals in Victoria (Australia).

stat.AP↗

arXiv2013

Spatio-Temporal Disease Surveillance: Forward Selection Scan Statistic

The scan statistic sets the benchmark for spatio-temporal surveillance methods with its popularity. In its simplest form it scans the target area and time to find regions with disease count higher than expected. If the shape and size of the disease outbreaks are known, then to detect it sufficiently early the scan statistic can design its search area to be efficient for this shape and size. A plan that is efficient at detecting a range of disease outbreak shapes and sizes is important because these vary from one outbreak to the next and are generally never known in advance. This paper offers a forward selection scan statistic that reduces the computational effort on the usual single window scan plan, while still offering greater flexibility in signalling outbreaks of varying shapes. The approach starts by dividing the target geographical regions into a lattice. Secondly it smooths the time series of lattice cell counts using multivariate exponential weighted moving averages. Thirdly, these EWMA cell counts are spatially smoothed to reduce spatial noise and leave the spatial signal. The fourth step uses forward selection approach to scanning mutually exclusive and exhaustive rectangular regions of dynamic dimensions. In the fifth step, it prunes away all insignificant scanned regions where counts are not significantly higher than expected. An outbreak is signaled if at least one region remains after pruning. If all regions are pruned away - including the scan of the target region, then no outbreak is signaled.

stat.AP↗

arXiv2013

Estimation of an Origin/Destination matrix: Application to a ferry transport data

The estimation of the number of passengers with the identical journey is a common problem for public transport authorities. This problem is also known as the Origin- Destination estimation (OD) problem and it has been widely studied for the past thirty years. However, the theory is missing when the observations are not limited to the passenger counts but also includes station surveys. Our aim is to provide a solid framework for the estimation of an OD matrix when only a portion of the journey counts are observable. Our method consists of a statistical estimation technique for OD matrix when we have the sum-of-row counts and survey-based observations. Our technique differs from the previous studies in that it does not need a prior OD matrix which can be hard to obtain. Instead, we model the passengers behavior through the survey data, and use the diagonalization of the partial OD matrix to reduce the space parameter and derive a consistent global OD matrix estimator. We demonstrate the robustness of our estimator and apply it to several examples showcasing the proposed models and approach. We highlight how other sources of data can be incorporated in the model such as explanatory variables, e.g. rainfall, indicator variables for major events, etc, and inference made in a principled, non-heuristic way.

stat.AP↗