Investigating Cross-Domain Binary Relation Classification in Biomedical Natural Language Processing.

This paper addresses the challenge of binary relation classification in biomedical Natural Language Processing (NLP), focusing on diverse domains including gene-disease associations, compound protein interactions, and social determinants of health (SDOH). We evaluate different approaches, including fine-tuning Bidirectional Encoder Representations from Transformers (BERT) models and generative Large Language Models (LLMs), and examine their performance in zero and few-shot settings. We also introduce a novel dataset of biomedical text annotated with social and clinical entities to facilitate research into relation classification. Our results underscore the continued complexity of this task for both humans and models. BERT-based models trained on domain-specific data excelled in certain domains and achieved comparable performance and generalization power to generative LLMs in others. Despite these encouraging results, these models are still far from achieving human-level performance. We also highlight the significance of high-quality training data and domain-specific fine-tuning on the performance of all the considered models.

Automated Feature Selection from Medical Literature.

We propose an automated approach to rank the most salient variables related to a certain clinical phenomenon from scientific literature. Our solution is an automated approach to improve the efficiency of the collection of different health-related measures from a population, and to accelerate the discovery of novel associations and dependencies between health-related concepts.

Automatic Mapping of Terminology Items with Transformers.

Biomedical ontologies are a key component in many systems for the analysis of textual clinical data. They are employed to organize information about a certain domain relying on a hierarchy of different classes. Each class maps a concept to items in a terminology developed by domain experts. These mappings are then leveraged to organize the information extracted by Natural Language Processing (NLP) models to build knowledge graphs for inferences. The creation of these associations, however, requires extensive manual review. In this paper, we present an automated approach and repeatable framework to learn a mapping between ontology classes and terminology terms derived from vocabularies in the Unified Medical Language System (UMLS) metathesaurus. According to our evaluation, the proposed system achieves a performance close to humans and provides a substantial improvement over existing systems developed by the National Library of Medicine to assist researchers through this process.

Identifying single-item faked responses in personality tests: A new TF-IDF-based method.

Faking in a psychological test is often observed whenever an examinee may gain an advantage from it. Although techniques are available to identify a faker, they cannot identify the specific questions distorted by faking. This work evaluates the effectiveness of term frequency-inverse document frequency (TF-IDF)-an information retrieval mathematical tool used in search engines and language representations-in identifying single-item faked responses. We validated the technique on three datasets containing responses to the 10-item Big Five questionnaire (total of 694 participants, respectively 221, 243, and 230) in three faking situations. Each participant responded twice, once faking to achieve an objective in one of three contexts (one to obtain child custody and two to land a job) and once honestly. The proposed TF-IDF model has proven very effective in separating honest from dishonest responses-with the honest ones having low TF-IDF values and the dishonest ones having higher values-and in identifying which of the 10 responses to the questionnaire were distorted in the dishonest condition. We also provide examples of the technique in a single-case evaluation.