Search

Deep learning models have shown their great performances in natural language processing tasks. While much attention has been paid towards improvements in utility, privacy leakage and social bias are two major concerns arising in trained models. In this paper, we protect individual privacy and mitigate gender bias on classification models simultaneously. First, we propose a selective privacy-preserving method that only obscure individuals' sensitive information by adding noise on word embeddings. Then we propose a negative multi-task learning framework to mitigate the gender bias which contains a main task and a gender prediction task. The main task uses a positive loss constraint to ensure utility while the gender prediction task applies a negative loss constraint to remove gender-specific features. We analyze two existing word embeddings and evaluate them on sentiment analysis and medical text classification tasks. Our experimental results show that our negative multi-task learning framework can mitigate the gender bias while keeping models’ utility on both sentiment analysis and medical text classification.

Background Clinical pharmacy plays an integral role in optimizing inpatient care. Nevertheless, prioritising patient care remains a critical challenge for pharmacists in a hectic medical ward. In Malaysia, clinical pharmacy practice has a paucity of standardized tools to prioritise patient care. Aim Our aim is to develop and validate a pharmaceutical assessment screening tool (PAST) to guide medical ward pharmacists in our local hospitals to effectively prioritise patient care. Method This study involved 2 major phases; (1) development of PAST through literature review and group discussion, (2) validation of PAST using a three-round Delphi survey. Twenty-four experts were invited by email to participate in the Delphi survey. In each round, experts were required to rate the relevance and completeness of PAST criteria and were given chance for open feedback. The 75% consensus benchmark was set and criteria with achieved consensus were retained in PAST. Experts’ suggestions were considered and added into PAST for rating. After each round, experts were provided with anonymised feedback and results from the previous round. Results Three Delphi rounds resulted in the final tool (rearranged as mnemonic ‘STORIMAP’). STORIMAP consists of 8 main criteria with 29 subcomponents. Marks are allocated for each criteria in STORIMAP which can be combined to a total of 15 marks. Patient acuity level is determined based on the final score and clerking priority is assigned accordingly. Conclusion STORIMAP potentially serves as a useful tool to guide medical ward pharmacists to prioritise patients effectively, hence establishing acuity-based pharmaceutical care.

Existing studies show that extracting a complete keyphrase candidate set is the first and crucial step to extract high quality keyphrases from documents. Based on a common sense that words do not repeatedly appear in an effective keyphrase, we propose a novel algorithm named KCSP for document-specific keyphrase candidate search using sequential pattern mining with gap constraints, which only needs to scan a document once and automatically specifies appropriate gap constraints for words without users’ participation. The experimental results confirm that it helps improve the quality of keyphrase extraction.

When labeling objects via Internet-based outsourcing systems, the labelers may have bias, because they lack expertise, dedication and personal preference. These reasons cause Imbalanced Multiple Noisy Labeling. To deal with the imbalance labeling issue, we propose an agnostic algorithm PLAT (Positive LAbel frequency Threshold) which does not need any information about quality of labelers and underlying class distribution. Simulations on eight real-world datasets with different underlying class distributions demonstrate that PLAT not only effectively deals with the imbalanced multiple noisy labeling problem that off-the-shelf agnostic methods cannot cope with, but also performs nearly the same as majority voting under the circumstances that labelers have no bias.

One-against-all and one-against-one are two popular methodologies for reducing multiclass classification problems into a set of binary classifications. In this paper, we are interested in the performance of both one-against-all and one-against-one for classification algorithms, such as decision tree, naïve bayes, support vector machine, and logistic regression. Since both one-against-all and one-against-one work like creating a classification committee, they are expected to improve the performance of classification algorithms. However, our experimental results surprisingly show that one-against-all worsens the performance of the algorithms on most datasets. One-against-one helps, but performs worse than the same iterations of bagging these algorithms. Thus, we conclude that both one-against-all and one-against-one should not be used for the algorithms that can perform multiclass classifications directly. Bagging is better approach for improving their performance.

Multi-label classifications exist in many real world applications. This paper empirically studies the performance of a variety of multi-label classification algorithms. Some of them are developed based on problem transformation. Some of them are developed based on adaption. Our experimental results show that the adaptive Multi-Label K-Nearest Neighbor performs the best, followed by Random k-Label Set, followed by Classifier Chain and Binary Relevance. Adaboost.MH performs the worst, followed by Pruned Problem Transformation. Our experimental results also provide us the confidence of the correlations among multi-labels. These insights shed light for future research directions on multi-label classifications.