Matteo Palmonari

Marco Ripamonti, Flavio De Paoli, Matteo Palmonari

The large availability of datasets fosters the use of \acrshort{ml} and \acrshort{ai} technologies to gather insights, study trends, and predict unseen behaviours out of the world of data. Today, gathering and integrating data from different sources is mainly a manual activity that requires the knowledge of expert users at an high cost in terms of both time and money. It is, therefore, necessary to make the process of gathering and linking data from many different sources affordable to make datasets ready to perform the desired analysis. In this work, we propose the development of a comprehensive framework, named SemTUI, to make the enrichment process flexible, complete, and effective through the use of semantics. The approach is to promote fast integration of external services to perform enrichment tasks such as reconciliation and extension; and to provide users with a graphical interface to support additional tasks, such as refinement to correct ambiguous results provided by automatic enrichment algorithms. A task-driven user evaluation proved SemTUI to be understandable, usable, and capable of achieving table enrichment with little effort and time with user tests that involved people with different skills and experiences.

Federico Belotti, Fabio Dadda, Marco Cremaschi et al.

Tables are crucial containers of information, but understanding their meaning may be challenging. Over the years, there has been a surge in interest in data-driven approaches based on deep learning that have increasingly been combined with heuristic-based ones. In the last period, the advent of \acf{llms} has led to a new category of approaches for table annotation. However, these approaches have not been consistently evaluated on a common ground, making evaluation and comparison difficult. This work proposes an extensive evaluation of four STI SOTA approaches: Alligator (formerly s-elbat), Dagobah, TURL, and TableLlama; the first two belong to the family of heuristic-based algorithms, while the others are respectively encoder-only and decoder-only Large Language Models (LLMs). We also include in the evaluation both GPT-4o and GPT-4o-mini, since they excel in various public benchmarks. The primary objective is to measure the ability of these approaches to solve the entity disambiguation task with respect to both the performance achieved on a common-ground evaluation setting and the computational and cost requirements involved, with the ultimate aim of charting new research paths in the field.

Riccardo Pozzi, Matteo Palmonari, Andrea Coletta et al.

Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as Retrieval-Augmented Generation (RAG) and tool use, aim to address these issues by incorporating external knowledge. Yet, they rely on additional models or services, resulting in complex pipelines, potential error propagation, and often requiring the model to process a large number of tokens. In this paper, we present a scalable method that enables LLMs to access external knowledge without depending on retrievers or auxiliary models. Our approach uses constrained generation with a pre-built prefix-tree index. Triples from a Knowledge Graph are verbalized in textual facts, tokenized, and indexed in a prefix tree for efficient access. During inference, to acquire external knowledge, the LLM generates facts with constrained generation which allows only sequences of tokens that form an existing fact. We evaluate our proposal on Question Answering and show that it scales to large knowledge bases (800 million facts), adapts to domain-specific data, and achieves effective results. These gains come with minimal generation-time overhead. ReFactX code is available at https://github.com/rpo19/ReFactX.

Davide Ghilardi, Federico Belotti, Marco Molinari et al.

SAEs have recently been employed as a promising unsupervised approach for understanding the representations of layers of Large Language Models (LLMs). However, with the growth in model size and complexity, training SAEs is computationally intensive, as typically one SAE is trained for each model layer. To address such limitation, we propose \textit{Group-SAE}, a novel strategy to train SAEs. Our method considers the similarity of the residual stream representations between contiguous layers to group similar layers and train a single SAE per group. To balance the trade-off between efficiency and performance, we further introduce \textit{AMAD} (Average Maximum Angular Distance), an empirical metric that guides the selection of an optimal number of groups based on representational similarity across layers. Experiments on models from the Pythia family show that our approach significantly accelerates training with minimal impact on reconstruction quality and comparable downstream task performance and interpretability over baseline SAEs trained layer by layer. This method provides an efficient and scalable strategy for training SAEs in modern LLMs.

Marco Cremaschi, Blerina Spahiu, Matteo Palmonari et al.

Tabular data plays a pivotal role in various fields, making it a popular format for data manipulation and exchange, particularly on the web. The interpretation, extraction, and processing of tabular information are invaluable for knowledge-intensive applications. Notably, significant efforts have been invested in annotating tabular data with ontologies and entities from background knowledge graphs, a process known as Semantic Table Interpretation (STI). STI automation aids in building knowledge graphs, enriching data, and enhancing web-based question answering. This survey aims to provide a comprehensive overview of the STI landscape. It starts by categorizing approaches using a taxonomy of 31 attributes, allowing for comparisons and evaluations. It also examines available tools, assessing them based on 12 criteria. Furthermore, the survey offers an in-depth analysis of the Gold Standards used for evaluating STI approaches. Finally, it provides practical guidance to help end-users choose the most suitable approach for their specific tasks while also discussing unresolved issues and suggesting potential future research directions.

Riccardo Pozzi, Valentina Barbera, Renzo Alva Principe et al.

Criminal investigations often involve the analysis of messages exchanged through instant messaging apps such as WhatsApp, which can be an extremely effort-consuming task. Our approach integrates knowledge graphs and NLP models to support this analysis by semantically enriching data collected from suspects' mobile phones, and help prosecutors and investigators search into the data and get valuable insights. Our semantic enrichment process involves extracting message data and modeling it using a knowledge graph, generating transcriptions of voice messages, and annotating the data using an end-to-end entity extraction approach. We adopt two different solutions to help users get insights into the data, one based on querying and visualizing the graph, and one based on semantic search. The proposed approach ensures that users can verify the information by accessing the original data. While we report about early results and prototypes developed in the context of an ongoing project, our proposal has undergone practical applications with real investigation data. As a consequence, we had the chance to interact closely with prosecutors, collecting positive feedback but also identifying interesting opportunities as well as promising research directions to share with the research community.

Federico Moiraghi, Matteo Palmonari, Davide Allavena et al.

Classifying public tenders is a useful task for both companies that are invited to participate and for inspecting fraudulent activities. To facilitate the task for both participants and public administrations, the European Union presented a common taxonomy (Common Procurement Vocabulary, CPV) which is mandatory for tenders of certain importance; however, the contracts in which a CPV label is mandatory are the minority compared to all the Public Administrations activities. Classifying over a real-world taxonomy introduces some difficulties that can not be ignored. First of all, some fine-grained classes have an insufficient (if any) number of observations in the training set, while other classes are far more frequent (even thousands of times) than the average. To overcome those difficulties, we present a zero-shot approach, based on a pre-trained language model that relies only on label description and respects the label taxonomy. To train our proposed model, we used industrial data, which comes from contrattipubblici.org, a service by SpazioDati s.r.l. that collects public contracts stipulated in Italy in the last 25 years. Results show that the proposed model achieves better performance in classifying low-frequent classes compared to three different baselines, and is also able to predict never-seen classes.

Carlo Bono, Federico Belotti, Matteo Palmonari

Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art performance in Entity Linking (EL) tasks, their deployment in real-world scenarios requires not only accurate predictions but also reliable uncertainty estimates, which require resource-demanding multi-shot inference, posing serious limits to their actual applicability. As a more efficient alternative, we investigate a self-supervised approach for estimating uncertainty from single-shot LLM outputs using token-level features, reducing the need for multiple generations. Evaluation is performed on an EL task on tabular data across multiple LLMs, showing that the resulting uncertainty estimates are highly effective in detecting low-accuracy outputs. This is achieved at a fraction of the computational cost, ultimately supporting a cost-effective integration of uncertainty measures into LLM-based EL workflows. The method offers a practical way to incorporate uncertainty estimation into EL workflows with limited computational overhead.

Giorgio Ottolina, Matteo Palmonari, Mehwish Alam et al.

State-of-the-art approaches for metaphor detection compare their literal - or core - meaning and their contextual meaning using metaphor classifiers based on neural networks. However, metaphorical expressions evolve over time due to various reasons, such as cultural and societal impact. Metaphorical expressions are known to co-evolve with language and literal word meanings, and even drive, to some extent, this evolution. This poses the question of whether different, possibly time-specific, representations of literal meanings may impact the metaphor detection task. To the best of our knowledge, this is the first study that examines the metaphor detection task with a detailed exploratory analysis where different temporal and static word embeddings are used to account for different representations of literal meanings. Our experimental analysis is based on three popular benchmarks used for metaphor detection and word embeddings extracted from different corpora and temporally aligned using different state-of-the-art approaches. The results suggest that the usage of different static word embedding methods does impact the metaphor detection task and some temporal word embeddings slightly outperform static methods. However, the results also suggest that temporal word embeddings may provide representations of the core meaning of the metaphor even too close to their contextual meaning, thus confusing the classifier. Overall, the interaction between temporal language evolution and metaphor detection appears tiny in the benchmark datasets used in our experiments. This suggests that future work for the computational analysis of this important linguistic phenomenon should first start by creating a new dataset where this interaction is better represented.

Federico Bianchi, Marco Marelli, Paolo Nicoli et al.

Understanding differences of viewpoints across corpora is a fundamental task for computational social sciences. In this paper, we propose the Sliced Word Embedding Association Test (SWEAT), a novel statistical measure to compute the relative polarization of a topical wordset across two distributional representations. To this end, SWEAT uses two additional wordsets, deemed to have opposite valence, to represent two different poles. We validate our approach and illustrate a case study to show the usefulness of the introduced measure.

Federico Bianchi, Gaetano Rossiello, Luca Costabello et al.

Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces. In this chapter, we introduce the reader to the concept of knowledge graph embeddings by explaining what they are, how they can be generated and how they can be evaluated. We summarize the state-of-the-art in this field by describing the approaches that have been introduced to represent knowledge in the vector space. In relation to knowledge representation, we consider the problem of explainability, and discuss models and methods for explaining predictions obtained via knowledge graph embeddings.

Federico Bianchi, Valerio Di Carlo, Paolo Nicoli et al.

Word2vec is one of the most used algorithms to generate word embeddings because of a good mix of efficiency, quality of the generated representations and cognitive grounding. However, word meaning is not static and depends on the context in which words are used. Differences in word meaning that depends on time, location, topic, and other factors, can be studied by analyzing embeddings generated from different corpora in collections that are representative of these factors. For example, language evolution can be studied using a collection of news articles published in different time periods. In this paper, we present a general framework to support cross-corpora language studies with word embeddings, where embeddings generated from different corpora can be compared to find correspondences and differences in meaning across the corpora. CADE is the core component of our framework and solves the key problem of aligning the embeddings generated from different corpora. In particular, we focus on providing solid evidence about the effectiveness, generality, and robustness of CADE. To this end, we conduct quantitative and qualitative experiments in different domains, from temporal word embeddings to language localization and topical analysis. The results of our experiments suggest that CADE achieves state-of-the-art or superior performance on tasks where several competing approaches are available, yet providing a general method that can be used in a variety of domains. Finally, our experiments shed light on the conditions under which the alignment is reliable, which substantially depends on the degree of cross-corpora vocabulary overlap.

Valerio Di Carlo, Federico Bianchi, Matteo Palmonari

Temporal word embeddings have been proposed to support the analysis of word meaning shifts during time and to study the evolution of languages. Different approaches have been proposed to generate vector representations of words that embed their meaning during a specific time interval. However, the training process used in these approaches is complex, may be inefficient or it may require large text corpora. As a consequence, these approaches may be difficult to apply in resource-scarce domains or by scientists with limited in-depth knowledge of embedding models. In this paper, we propose a new heuristic to train temporal word embeddings based on the Word2vec model. The heuristic consists in using atemporal vectors as a reference, i.e., as a compass, when training the representations specific to a given time interval. The use of the compass simplifies the training process and makes it more efficient. Experiments conducted using state-of-the-art datasets and methodologies suggest that our approach outperforms or equals comparable approaches while being more robust in terms of the required corpus size.