Gabriella Pasi

Gian Carlo Milanese, Gabriella Pasi

Order-Sorted Feature (OSF) logic is a knowledge representation and reasoning language based on function-denoting feature symbols and set-denoting sort symbols ordered in a subsumption lattice. OSF logic allows the construction of record-like terms that represent classes of entities and that are themselves ordered in a subsumption relation. The unification algorithm for such structures provides an efficient calculus of type subsumption, which has been applied in computational linguistics and implemented in constraint logic programming languages such as LOGIN and LIFE and automated reasoners such as CEDAR. This work generalizes OSF logic to a fuzzy setting. We give a flexible definition of a fuzzy subsumption relation which generalizes Zadeh's inclusion between fuzzy sets. Based on this definition we define a fuzzy semantics of OSF logic where sort symbols and OSF terms denote fuzzy sets. We extend the subsumption relation to OSF terms and prove that it constitutes a fuzzy partial order with the property that two OSF terms are subsumed by one another in the crisp sense if and only if their subsumption degree is greater than 0. We show how to find the greatest lower bound of two OSF terms by unifying them and how to compute the subsumption degree between two OSF terms, and we provide the complexity of these operations.

Georgios Peikos, Oscar Espitia, Gabriella Pasi

This contribution summarizes the participation of the UNIMIB team to the TREC 2021 Clinical Trials Track. We have investigated the effect of different query representations combined with several retrieval models on the retrieval performance. First, we have implemented a neural re-ranking approach to study the effectiveness of dense text representations. Additionally, we have investigated the effectiveness of a novel decision-theoretic model for relevance estimation. Finally, both of the above relevance models have been compared with standard retrieval approaches. In particular, we combined a keyword extraction method with a standard retrieval process based on the BM25 model and a decision-theoretic relevance model that exploits the characteristics of this particular search task. The obtained results show that the proposed keyword extraction method improves 84% of the queries over the TREC's median NDCG@10 measure when combined with either traditional or decision-theoretic relevance models. Moreover, regarding RPEC@10, the employed decision-theoretic model improves 85% of the queries over the reported TREC's median value.

Georgios Peikos, Symeon Symeonidis, Pranav Kasela et al.

Clinical trials are a critical component of evaluating the effectiveness of new medical interventions and driving advancements in medical research. Therefore, timely enrollment of patients is crucial to prevent delays or premature termination of trials. In this context, Electronic Health Records (EHRs) have emerged as a valuable tool for identifying and enrolling eligible participants. In this study, we propose an automated approach that leverages ChatGPT, a large language model, to extract patient-related information from unstructured clinical notes and generate search queries for retrieving potentially eligible clinical trials. Our empirical evaluation, conducted on two benchmark retrieval collections, shows improved retrieval performance compared to existing approaches when several general-purposed and task-specific prompts are used. Notably, ChatGPT-generated queries also outperform human-generated queries in terms of retrieval performance. These findings highlight the potential use of ChatGPT to enhance clinical trial enrollment while ensuring the quality of medical service and minimizing direct risks to patients.

Rishabh Upadhyay, Arian Askari, Gabriella Pasi et al.

In this paper, we propose a novel approach to consider multiple dimensions of relevance beyond topicality in cross-encoder re-ranking. On the one hand, current multidimensional retrieval models often use naïve solutions at the re-ranking stage to aggregate multiple relevance scores into an overall one. On the other hand, cross-encoder re-rankers are effective in considering topicality but are not designed to straightforwardly account for other relevance dimensions. To overcome these issues, we envisage enhancing the candidate documents -- which are retrieved by a first-stage lexical retrieval model -- with "relevance statements" related to additional dimensions of relevance and then performing a re-ranking on them with cross-encoders. In particular, here we consider an additional relevance dimension beyond topicality, which is credibility. We test the effectiveness of our solution in the context of the Consumer Health Search task, considering publicly available datasets. Our results show that the proposed approach statistically outperforms both aggregation-based and cross-encoder re-rankers.

Wojciech Kusa, Óscar E. Mendoza, Petr Knoth et al.

Clinical trials (CTs) often fail due to inadequate patient recruitment. This paper tackles the challenges of CT retrieval by presenting an approach that addresses the patient-to-trials paradigm. Our approach involves two key components in a pipeline-based model: (i) a data enrichment technique for enhancing both queries and documents during the first retrieval stage, and (ii) a novel re-ranking schema that uses a Transformer network in a setup adapted to this task by leveraging the structure of the CT documents. We use named entity recognition and negation detection in both patient description and the eligibility section of CTs. We further classify patient descriptions and CT eligibility criteria into current, past, and family medical conditions. This extracted information is used to boost the importance of disease and drug mentions in both query and index for lexical retrieval. Furthermore, we propose a two-step training schema for the Transformer network used to re-rank the results from the lexical retrieval. The first step focuses on matching patient information with the descriptive sections of trials, while the second step aims to determine eligibility by matching patient information with the criteria section. Our findings indicate that the inclusion criteria section of the CT has a great influence on the relevance score in lexical models, and that the enrichment techniques for queries and documents improve the retrieval of relevant trials. The re-ranking strategy, based on our training schema, consistently enhances CT retrieval and shows improved performance by 15\% in terms of precision at retrieving eligible trials. The results of our experiments suggest the benefit of making use of extracted entities. Moreover, our proposed re-ranking schema shows promising effectiveness compared to larger neural models, even with limited training data.

Marco Braga, Pranav Kasela, Alessandro Raganato et al.

Large Language Models (LLMs) have shown impressive zero-shot performance across a variety of Natural Language Processing tasks, including document re-ranking. However, their effectiveness degrades on unseen tasks and domains, largely due to shifts in vocabulary and word distributions. In this paper, we investigate Task Arithmetic, a technique that combines the weights of LLMs pre-trained on different tasks or domains via simple mathematical operations, such as addition or subtraction, to adapt retrieval models without requiring additional fine-tuning. Our method is able to synthesize diverse tasks and domain knowledge into a single model, enabling effective zero-shot adaptation in different retrieval contexts. Extensive experiments on publicly available scientific, biomedical, and multilingual datasets show that our method improves state-of-the-art re-ranking performance by up to 18% in NDCG@10 and 15% in P@10. In addition to these empirical gains, our analysis provides insights into the strengths and limitations of Task Arithmetic as a practical strategy for zero-shot learning and model adaptation. We make our code publicly available at https://github.com/DetectiveMB/Task-Arithmetic-for-ZS-IR.

Effrosyni Sokli, Pranav Kasela, Georgios Peikos et al.

Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were trained on. To address this challenge, prior research in IR incorporated the Mixture-of-Experts (MoE) framework within each Transformer layer of a DRM, which, though effective, substantially increased the number of additional parameters. In this paper, we propose a more efficient design, which introduces a single MoE block (SB-MoE) after the final Transformer layer. To assess the retrieval effectiveness of SB-MoE, we perform an empirical evaluation across three IR tasks. Our experiments involve two evaluation setups, aiming to assess both in-domain effectiveness and the model's zero-shot generalizability. In the first setup, we fine-tune SB-MoE with four different underlying DRMs on seven IR benchmarks and evaluate them on their respective test sets. In the second setup, we fine-tune SB-MoE on MSMARCO and perform zero-shot evaluation on thirteen BEIR datasets. Additionally, we perform further experiments to analyze the model's dependency on its hyperparameters (i.e., the number of employed and activated experts) and investigate how this variation affects SB-MoE's performance. The obtained results show that SB-MoE is particularly effective for DRMs with lightweight base models, such as TinyBERT and BERT-Small, consistently exceeding standard model fine-tuning across benchmarks. For DRMs with more parameters, such as BERT-Base and Contriever, our model requires a larger number of training samples to achieve improved retrieval performance. Our code is available online at: https://github.com/FaySokli/SB-MoE.

Marco Braga, Gian Carlo Milanese, Gabriella Pasi

Text preprocessing is a fundamental component of Natural Language Processing, involving techniques such as stopword removal, stemming, and lemmatization to prepare text as input for further processing and analysis. Despite the context-dependent nature of the above techniques, traditional methods usually ignore contextual information. In this paper, we investigate the idea of using Large Language Models (LLMs) to perform various preprocessing tasks, due to their ability to take context into account without requiring extensive language-specific annotated resources. Through a comprehensive evaluation on web-sourced data, we compare LLM-based preprocessing (specifically stopword removal, lemmatization and stemming) to traditional algorithms across multiple text classification tasks in six European languages. Our analysis indicates that LLMs are capable of replicating traditional stopword removal, lemmatization, and stemming methods with accuracies reaching 97%, 82%, and 74%, respectively. Additionally, we show that ML algorithms trained on texts preprocessed by LLMs achieve an improvement of up to 6% with respect to the $F_1$ measure compared to traditional techniques. Our code, prompts, and results are publicly available at https://github.com/GianCarloMilanese/llm_pipeline_wi-iat.

Effrosyni Sokli, Pranav Kasela, Georgios Peikos et al.

While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE) architecture. While previous IR studies have incorporated MoE architectures within the Transformer layers of DRMs, our work investigates an architecture that integrates a single MoE block (SB-MoE) after the output of the final Transformer layer. Our empirical evaluation investigates how SB-MoE compares, in terms of retrieval effectiveness, to standard fine-tuning. In detail, we fine-tune three DRMs (TinyBERT, BERT, and Contriever) across four benchmark collections with and without adding the MoE block. Moreover, since MoE showcases performance variations with respect to its parameters (i.e., the number of experts), we conduct additional experiments to investigate this aspect further. The findings show the effectiveness of SB-MoE especially for DRMs with a low number of parameters (i.e., TinyBERT), as it consistently outperforms the fine-tuned underlying model on all four benchmarks. For DRMs with a higher number of parameters (i.e., BERT and Contriever), SB-MoE requires larger numbers of training samples to yield better retrieval performance.

Filip Ilievski, Barbara Hammer, Frank van Harmelen et al.

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of AI and its participation in human-AI teams increasingly shows the need for AI alignment, that is, to make AI systems act according to our preferences. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise. In cognitive science, human generalisation commonly involves abstraction and concept learning. In contrast, AI generalisation encompasses out-of-domain generalisation in machine learning, rule-based reasoning in symbolic AI, and abstraction in neurosymbolic AI. In this perspective paper, we combine insights from AI and cognitive science to identify key commonalities and differences across three dimensions: notions of, methods for, and evaluation of generalisation. We map the different conceptualisations of generalisation in AI and cognitive science along these three dimensions and consider their role for alignment in human-AI teaming. This results in interdisciplinary challenges across AI and cognitive science that must be tackled to provide a foundation for effective and cognitively supported alignment in human-AI teaming scenarios.

Alessandro Raganato, Rafael Peñaloza, Marco Viviani et al.

Large Language Models (LLMs) have shown remarkable capabilities in manipulating natural language across multiple applications, but their ability to handle simple reasoning tasks is often questioned. In this work, we aim to provide a comprehensive analysis of LLMs' reasoning competence, specifically focusing on their prompt dependency. In particular, we introduce a new benchmark dataset with a series of simple reasoning questions demanding shallow logical reasoning. Aligned with cognitive psychology standards, the questions are confined to a basic domain revolving around geometric figures, ensuring that responses are independent of any pre-existing intuition about the world and rely solely on deduction. An empirical analysis involving zero-shot and few-shot prompting across 24 LLMs of different sizes reveals that, while LLMs with over 70 billion parameters perform better in the zero-shot setting, there is still a large room for improvement. An additional test with chain-of-thought prompting over 22 LLMs shows that this additional prompt can aid or damage the performance of models, depending on whether the rationale is required before or after the answer.

Federico Cabitza, Davide Ciucci, Gabriella Pasi et al.

This article discusses open problems, implemented solutions, and future research in the area of responsible AI in healthcare. In particular, we illustrate two main research themes related to the work of two laboratories within the Department of Informatics, Systems, and Communication at the University of Milano-Bicocca. The problems addressed concern, in particular, {uncertainty in medical data and machine advice}, and the problem of online health information disorder.

Arian Askari, Suzan Verberne, Gabriella Pasi

Expert finding has been well-studied in community question answering (QA) systems in various domains. However, none of these studies addresses expert finding in the legal domain, where the goal is for citizens to find lawyers based on their expertise. In the legal domain, there is a large knowledge gap between the experts and the searchers, and the content on the legal QA websites consist of a combination formal and informal communication. In this paper, we propose methods for generating query-dependent textual profiles for lawyers covering several aspects including sentiment, comments, and recency. We combine query-dependent profiles with existing expert finding methods. Our experiments are conducted on a novel dataset gathered from an online legal QA service. We discovered that taking into account different lawyer profile aspects improves the best baseline model. We make our dataset publicly available for future work.

Gabriella Pasi, Rafael Peñaloza

A prominent problem in knowledge representation is how to answer queries taking into account also the implicit consequences of an ontology representing domain knowledge. While this problem has been widely studied within the realm of description logic ontologies, it has been surprisingly neglected within the context of vague or imprecise knowledge, particularly from the point of view of mathematical fuzzy logic. In this paper we study the problem of answering conjunctive queries and threshold queries w.r.t. ontologies in fuzzy DL-Lite. Specifically, we show through a rewriting approach that threshold query answering w.r.t. consistent ontologies remains in $AC_0$ in data complexity, but that conjunctive query answering is highly dependent on the selected triangular norm, which has an impact on the underlying semantics. For the idempodent Gödel t-norm, we provide an effective method based on a reduction to the classical case. This paper is under consideration in Theory and Practice of Logic Programming (TPLP).