Questionnaire Free Text Summarisation Using Hierarchical Classification

An investigation into the potential effectiveness of generating text classifiers from secondary data for the purpose of text summarisation is described. The application scenario assumes a questionnaire corpus where we wish to provide a summary regarding the nature of the free text element of such questionnaires, but no suitable training data is available. The advocated approach is to build the desired text summarisation classifiers using secondary data and then apply these classifiers, for the purpose of text summarisation, to the primary data. We refer to this approach using the acronym CGUSD (Classifier Generation Using Secondary Data). The approach is evaluated using real questionnaire data obtained as part of the SAVSNET (Small Animal Veterinary Surveillance Network) project.KeywordsText SummarisationText Classification Using Secondary Data

Due to the complex label hierarchy and intensive labeling cost in practice, the hierarchical text classification (HTC) suffers a poor performance especially when low-resource or few-shot settings are considered. Recently, there is a growing trend of applying prompts on pre-trained language models (PLMs), which has exhibited effectiveness in the few-shot flat text classification tasks. However, limited work has studied the paradigm of prompt-based learning in the HTC problem when the training data is extremely scarce. In this work, we define a path-based few-shot setting and establish a strict path-based evaluation metric to further explore few-shot HTC tasks. To address the issue, we propose the hierarchical verbalizer (“HierVerb”), a multi-verbalizer framework treating HTC as a single- or multi-label classification problem at multiple layers and learning vectors as verbalizers constrained by hierarchical structure and hierarchical contrastive learning. In this manner, HierVerb fuses label hierarchy knowledge into verbalizers and remarkably outperforms those who inject hierarchy through graph encoders, maximizing the benefits of PLMs. Extensive experiments on three popular HTC datasets under the few-shot settings demonstrate that prompt with HierVerb significantly boosts the HTC performance, meanwhile indicating an elegant way to bridge the gap between the large pre-trained model and downstream hierarchical classification tasks.

Hierarchical classification has been becoming a popular research topic nowadays, particularly on the web as text categorization. For a large web corpus, there can be a hierarchy with hundreds of thousands of topics, so it is common to handle this task using a flat classification approach, inducing a binary classifier only for the leaf-node classes. However, it always suffers from such low prediction accuracy due to an imbalanced issue in the training data. In this paper, we propose two novel strategies: (i) “Top-Level Pruning” to narrow down the candidate classes, and (ii) “Exclusive Top-Level Training Policy” to build more effective classifiers by utilizing the top-level data. The experiments on the Wikipedia dataset show that our system outperforms the traditional flat approach unanimously on all hierarchical classification metrics.

Although an improvement of hierarchical text classification can be achieved by using hierarchical structure information, existing hierarchical text classification methods suffer from two problems: data skew (especially in large-scale hierarchy) and error propagation. In this paper, we first define the concept of path-based semantic vector for the presentation of categories. Then a set of additional reliable training data for data-sparse categories can be retrieved based on such representation and particular similarity metrics. This training data enhancement strategy is classifier independent and can improve the classification of categories without adequate training data. Second, we propose the occurrence probability based strategy for hierarchical text classification which can reduce error propagation efficiently. Cooccurrence probability is then introduced to correct the errors occurred on higher levels of the hierarchy. Extensive experiments show that our hierarchical classification strategies perform well on ODP dataset, even in the condition of having few training data.

In this paper, a hierarchical ensemble classification approach that utilizes a Directed Acyclic Graph (DAG) structure is proposed as a solution to the multi-class classification problem. Two main DAG structures are considered: (i) rooted DAG, and (ii) non-rooted DAG. The main challenges that are considered in this paper are: (i) the successive misclassification issue associated with hierarchical classification, and (i) identification of the starting node within the non-rooted DAG approach. To address these issues the idea is to utilize Bayesian probability values to: select the best starting DAG node, and to dictate whether single or multiple paths should be followed within the DAG structure. The reported experimental results indicated that the proposed DAG structure is more effective than when using a simple binary tree structure for generating a hierarchical classification model.

Hierarchy-Aware and Label Balanced Model for Hierarchical Text Classification

Web document hierarchical classification approaches often rely on textual features alone even though web pages include multimedia data. We propose a new hierarchical integrated web classification approach that combines image-based and text-based approaches. Instead of using a flat classifier to combine text and image classification, we perform classification on a hierarchy differently on different levels of the tree, using text for branches and images only at leaves. The results of our experiments show that the use of the hierarchical structure improved web document classification performance significantly.

IntroductionThe myoelectric control strategy, based on surface electromyographic signals, has long been used for controlling a prosthetic system with multiple degrees of freedom. Several methods classify gestures and force levels but the simultaneous real-time control of hand/wrist gestures and force levels did not yet reach a satisfactory level of effectiveness.MethodsIn this work, the hierarchical classification approach, already validated on 31 healthy subjects, was adapted for the real-time control of a multi-DoFs prosthetic system on 15 trans-radial amputees. The effectiveness of the hierarchical classification approach was assessed by evaluating both offline and real-time performance using three algorithms: Logistic Regression (LR), Non-linear Logistic Regression (NLR), and Linear Discriminant Analysis (LDA).ResultsThe results of this study showed the offline performance of amputees was promising and comparable to healthy subjects, with mean F1 scores of over 90% for the “Hand/wrist gestures classifier” and 95% for the force classifiers, implemented with the three algorithms with features extraction (FE). Another significant finding of this study was the feasibility of using the hierarchical classification strategy for real-time applications, due to its ability to provide a response time of 100 ms while maintaining an average online accuracy of above 90%.DiscussionA possible solution for real-time control of both hand/wrist gestures and force levels is the combined use of the LR algorithm with FE for the "Hand/wrist gestures classifier", and the NLR with FE for the Spherical and Tip force classifiers.

Chocolate has long been recognised as, and remains, a common cause of intoxication in dogs accounting for 25 per cent of acute presentations for intoxication.1 2 Case numbers in Europe...

Hierarchical multi-label text classification (HMTC) has become rather challenging when it requires handling large sets of closely related categories. We present a novel software that provides a hybrid embedding-based text representation for HMTC, shortened as HE-HMTC. It made full use of categories’ structure and their labels semantics to enrich the text representation, and therefore attempted to improve the classification performance of the text. In addition, HE-HMTC facilitates improving the accuracy of HMTC tasks. Moreover, our HE-HMTC can easily be generalized in other hierarchical classification tasks and achieve superior performance.

Patient monitoring systems are becoming increasingly important in accurately diagnosing and treating growing worldwide chronic conditions especially the obesity epidemic. The ubiquitous nature of wearable sensors, such as the readily available embedded accelerometers in smart phones, provides physicians with an opportunity to remotely monitor their patient's daily activity. There have been several developments in the area of activity recognition using wearable sensors. However, due to power constraints, resource efficient algorithms are necessary in order to perform accurate realtime activity recognition while consuming minimal energy. In this paper, we present a two-tier architecture for optimizing power consumption in such systems. While the first tier relies on a hierarchical classification approach, the second one manages the activation and deactivation of the classification system. We demonstrate this using a series of binary Support Vector Machine classifiers. The proposed approach, however, is classifier independent. Experimenting with subjects performing different daily activities such as walking, going upstairs and down-stairs, standing and sitting, our approach achieves a power savings of 87%, while maintaining 92% classification accuracy.

Multidimensional hierarchical classification

Twitter is a micro logging service where worldwide users publish and share their feelings. However, sentiment analysis for Twitter messages ('tweets') is regarded as a challenging problem because tweets are short and informal. In this paper, we apply a novel approach for automatically classifying the sentiment and emotions of Twitter messages. These messages are hierarchically categorized on basis of neutrality, polarity (positive or negative) and presence of various emotions. The hierarchical classification approach (HC) is a specialization of the well-known flat classification task. The main difference between them is that when using HC, examples must be assigned to classes organized in a previously defined class hierarchy, while traditional flat classification does not take into account the hierarchical information. We applied our model to posts collected from Twitter regarding the 2011 season of the Brazilian Soccer League. Our results show that the proposed method outperforms the corresponding flat approach in emotion classification.

We recently wrote a letter reporting a potential outbreak of prolific vomiting in dogs with prolonged lethargy and inappetence, sometimes with diarrhoea ( VR , 15 February 2020, vol 186,...

Ticks are an important driver of veterinary health care, causing irritation and sometimes infection to their hosts. We explored epidemiological and geo-referenced data from > 7 million electronic health records (EHRs) from cats and dogs collected by the Small Animal Veterinary Surveillance Network (SAVSNET) in Great Britain (GB) between 2014 and 2021 to assess the factors affecting tick attachment in an individual and at a spatiotemporal level. EHRs in which ticks were mentioned were identified by text mining; domain experts confirmed those with ticks on the animal. Tick presence/absence records were overlaid with a spatiotemporal series of climate, environment, anthropogenic and host distribution factors to produce a spatiotemporal regression matrix. An ensemble machine learning spatiotemporal model was used to fine-tune hyperparameters for Random Forest, Gradient-boosted Trees and Generalized Linear Model regression algorithms, which were then used to produce a final ensemble meta-learner to predict the probability of tick attachment across GB at a monthly interval and averaged long-term through 2014-2021 at a spatial resolution of 1km. Individual host factors associated with tick attachment were also assessed by conditional logistic regression on a matched case-control dataset. In total, 11,741 consultations were identified in which a tick was recorded. The frequency of tick records was low (0.16% EHRs), suggesting an underestimation of risk. That said, increased odds for tick attachment in cats and dogs were associated with younger adult ages, longer coat length, crossbreeds and unclassified breeds. In cats, males and entire animals had significantly increased odds of recorded tick attachment. The key variables controlling the spatiotemporal risk for tick attachment were climatic (precipitation and temperature) and vegetation type (Enhanced Vegetation Index). Suitable areas for tick attachment were predicted across GB, especially in forests and grassland areas, mainly during summer, particularly in June. Our results can inform targeted health messages to owners and veterinary practitioners, identifying those animals, seasons and areas of higher risk for tick attachment and allowing for more tailored prophylaxis to reduce tick burden, inappropriate parasiticide treatment and potentially TBDs in companion animals and humans. Sentinel networks like SAVSNET represent a novel complementary data source to improve our understanding of tick attachment risk for companion animals and as a proxy of risk to humans.