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 Large Language Models (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 uniquely compares Semantic Table Interpretation (STI) approaches with generative and encoder-only LLMs on diverse datasets. In particular, we conduct an extensive evaluation of four STI state-of-the-art (SOTA) approaches — Alligator (formerly s-elBat ), TURL , TableLlama , and DAGOBAH (the latter with a partial evaluation due to its high computational demands); Alligator and DAGOBAH belong to the family of heuristic-based algorithms, while TURL and TableLlama are respectively encoder-only and decoder-only 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 concerning both the performance achieved on a common-ground evaluation setting and the computational and cost requirements involved, either monetary or in terms of computational resources, with the ultimate aim of charting new research paths in the field.

Sparse Autoencoders (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 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 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.

DAVE is a framework for assisting the analysis of documents in knowledge-intensive domains, based on an entity-centric approach supported by annotations of named entities in the documents. DAVE supports search & filtering, document exploration, question answering, and knowledge refinement. It is released as an open-source project that the community can further develop. DAVE’s distinguishing features are: the integration of a chatbot interface based on recent RAG solutions into well-established entity-powered faceted search, the fusion of search and filtering features provided by entity-level annotations with the capability to ask questions on annotated documents; human-in-the-loop functions to consolidate knowledge while exploring information, allowing users to improve annotations from NLP algorithms.

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: Spazio Dati.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.

Algorithms are vulnerable to biases that might render their decisions unfair toward particular groups of individuals. Fairness comes with a range of facets that strongly depend on the application domain and that need to be enforced accordingly. However, most mitigation models embed fairness constraints as fundamental component of the loss function thus requiring code-level adjustments to adapt to specific contexts and domains. Rather than relying on a procedural approach, our model leverages declarative structured knowledge to encode fairness requirements in the form of logic rules capturing unambiguous and precise natural language statements. We propose a neuro-symbolic integration approach based on Logic Tensor Networks that combines data-driven network-based learning with high-level logical knowledge, allowing to perform classification tasks while reducing discrimination. Experimental evidence shows that performance is as good as state-of-the-art (SOTA) thus providing a flexible framework to account for non-discrimination often at a modest cost in terms of accuracy.

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.

Abstract Processing large-scale and highly interconnected Knowledge Graphs (KG) is becoming crucial for many applications such as recommender systems, question answering, etc. Profiling approaches have been proposed to summarize large KGs with the aim to produce concise and meaningful representation so that they can be easily managed. However, constructing profiles and calculating several statistics such as cardinality descriptors or inferences are resource expensive. In this paper, we present ABSTAT-HD, a highly distributed profiling tool that supports users in profiling and understanding big and complex knowledge graphs. We demonstrate the impact of the new architecture of ABSTAT-HD by presenting a set of experiments that show its scalability with respect to three dimensions of the data to be processed: size, complexity and workload. The experimentation shows that our profiling framework provides informative and concise profiles, and can process and manage very large KGs.

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.

Table annotation is a key task to improve querying the Web and support the Knowledge Graph population from legacy sources (tables). Last year, the SemTab challenge was introduced to unify different efforts to evaluate table annotation algorithms by providing a common interface and several general-purpose datasets as a ground truth. The SemTab dataset is useful to have a general understanding of how these algorithms work, and the organizers of the challenge included some artificial noise to the data to make the annotation trickier. However, it is hard to analyze specific aspects in an automatic way. For example, the ambiguity of names at the entity-level can largely affect the quality of the annotation. In this paper, we propose a novel dataset to complement the datasets proposed by SemTab. The dataset consists of a set of high-quality manually-curated tables with non-obviously linkable cells, i.e., where values are ambiguous names, typos, and misspelled entity names not appearing in the current version of the SemTab dataset. These challenges are particularly relevant for the ingestion of structured legacy sources into existing knowledge graphs. Evaluations run on this dataset show that ambiguity is a key problem for entity linking algorithms and encourage a promising direction for future work in the field.

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.

Faceted interfaces are omnipresent on the web to support data exploration and filtering. A facet is a triple: a domain (e.g., Book), a property (e.g., author, language), and a set of property values (e.g., Austen, Beauvoir, Coelho, Dostoevsky, Eco, Kerouac, Suskind, ..., French, English, German, Italian, Portuguese, Russian, ... ). Given a property (e.g., language), selecting one or more of its values (English and Italian) returns the domain entities (of type Book) that match the given values (the books that are written in English or Italian). To implement faceted interfaces in a way that is scalable to very large datasets, it is necessary to automate facet extraction. Prior work associates a facet domain with a set of homogeneous values, but does not annotate the facet property. In this paper, we annotate the facet property with a predicate from a reference Knowledge Base (KB) so as to maximize the semantic similarity between the property and the predicate. We define semantic similarity in terms of three new metrics: specificity, coverage, and frequency. Our experimental evaluation uses the DBpedia and YAGO KBs and shows that for the facet annotation problem, we obtain better results than a state-of-the-art approach for the annotation of web tables as modified to annotate a set of values.

Automatic matching systems are introduced to reduce the manual workload of users that need to align two ontologies by finding potential mappings and determining which ones should be included in a final alignment. Mappings found by fully automatic matching systems are neither correct nor complete when compared to gold standards. In addition, automatic matching systems may not be able to decide which one, among a set of candidate target concepts, is the best match for a source concept based on the available evidence. To handle the above mentioned problems, we present an interactive mapping Web tool named ICLM (Interactive Cross-lingual Mapping), which aims to improve an alignment computed by an automatic matching system by incorporating the feedback of multiple users. Users are asked to validate mappings computed by the automatic matching system by selecting the best match among a set of candidates, i.e., by performing a mapping selection task. ICLM tries to reduce users' effort required to validate mappings. ICLM distributes the mapping selection tasks to users based on the tasks' difficulty, which is estimated by considering the lexical characterization of the ontology concepts, and the confidence of automatic matching algorithms. Accordingly, ICLM estimates the effort (number of users) needed to validate the mappings. An experiment with several users involved in the alignment of large lexical ontologies is discussed in the paper, where different strategies for distributing the workload among the users are evaluated. Experimental results show that ICLM significantly improves the accuracy of the final alignment using the strategies proposed to balance and reduce the user workload.

Accessing or integrating data lexicalized in different languages is a challenge. Multilingual lexical resources play a fundamental role in reducing the language barriers to map concepts lexicalized in different languages. In this paper we present a large-scale study on the effectiveness of automatic translations to support two key cross-lingual ontology mapping tasks: the retrieval of candidate matches and the selection of the correct matches for inclusion in the final alignment. We conduct our experiments using four different large gold standards, each one consisting of a pair of mapped wordnets, to cover four different families of languages. We categorize concepts based on their lexicalization (type of words, synonym richness, position in a subconcept graph) and analyze their distributions in the gold standards. Leveraging this categorization, we measure several aspects of translation effectiveness, such as word-translation correctness, word sense coverage, synset and synonym coverage. Finally, we thoroughly discuss several findings of our study, which we believe are helpful for the design of more sophisticated cross-lingual mapping algorithms.

In this paper, we introduce a methodology for mapping linguistic ontologies lexicalized across different languages.We present a classification-based semantics for mappings of lexicalized concepts across different languages.We propose an experiment for validating the proposed cross-language mapping semantics, and discuss its role in creating a gold standard that can be used in assessing cross-language matching systems.

Autocompletion systems support users in the formulation of queries in different situations, from development environments to the web. In this paper we describe Composite Match Autocompletion (COMMA), a lightweight approach to the introduction of sema

The increasing number of services available on the Web requires sophisticated mechanisms for the matchmaking, selection and composition of services based on business criteria. Such mechanisms require descriptions that address business terms, but existing approaches for the modeling of service properties are inadequate for expressing business conditions. In this paper, we propose a novel Service Description Language for Contract specification (SeDL-C). The proposal is based on a detailed analysis of business terms to identify the set of requirements a model and a language should fulfill. Formal syntax and semantics for SeDL-C are given.

When compared to a gold standard, the set of mappings that are generated by an automatic ontology matching process is neither complete nor are the individual mappings always correct. However, given the explosion in the number, size, and complexity of available ontologies, domain experts no longer have the capability to create ontology mappings without considerable effort. We present a solution to this problem that consists of making the ontology matching process interactive so as to incorporate user feedback in the loop. Our approach clusters mappings to identify where user feedback will be most beneficial in reducing the number of user interactions and system iterations. This feedback process has been implemented in the Agreement Maker system and is supported by visual analytic techniques that help users to better understand the matching process. Experimental results using the OAEI benchmarks show the effectiveness of our approach. We will demonstrate how users can interact with the ontology matching process through the Agreement Maker user interface to match real-world ontologies.

Autocompletion systems support users in the formulation of queries in different computer systems, from development environments to the web. In this paper we describe Composite Match Autocompletion (COMMA), a lightweight approach to the introduction of semantics in the realization of a semi-structured data auto completion matching algorithm. The approach is formally described, then it is applied and evaluated with specific reference to the e-commerce context. The semantic extension to the matching algorithm exploits available information about product categories and distinguishing features of products to enhance the elaboration of exploratory queries. COMMA supports a seamless management of both targeted/precise queries and exploratory/vague ones, combining different filtering and scoring techniques. The algorithm is evaluated with respect both to effectiveness and efficiency in a real-world scenario: the achieved improvement is significant and not associated to a sensible increase of computational costs.

Integrated repositories of conceptual schemas provide organizations dealing with a large amount of data sources with an integrated view on the information they manage. Making schema repositories compliant with the Web and with the Web knowledge technologies has become crucial today. In this paper we present an approach to conceptual metadata management based on the design and the publication of repositories of linked Web schemas organized by abstraction. Schemas and schema mappings are represented in the repositories by means of a SKOS extension defined in the paper. The language makes the schemas reciprocally cross-linked, providing native Web-based browsing and search functionalities. Abstraction-based schema integration primitives provide the building blocks for the organization of the repositories: loose schema mappings are based on abstraction relations and the repository is organized into levels of abstraction; the design of the repository is based on the progressive abstraction and integration of source schemas. The approach is compliant with state-of-the-art tools developed in the semantic Web, which provide tool support for the design and publication on the Web of repositories of linked schemas.

Conceptual schema integration can be exploited at the conceptual metadata level to provide organizations that deal with a large amount of data sources with an integrated view on the overall information managed. In this paper we discuss the kind of language that can be exploited for such conceptual-level integration tasks in the large, and we introduce the ER dialect called Abstract ERIA (AERIA). The introduction of such a language is based on theoretical considerations and on past experiences in conceptual schema integration. The language is provided with a Web compliant front-end concrete syntax based on OWL-DL to support the compact design of the schema and the definition of integration and abstraction relations between the schema elements. A formal semantic interpretation of the AERIA language is discussed; this interpretation allows for a translation of AERIA schemas into standard Web ontologies to support model reuse and exchange.

In this paper we propose a meta-model for nonfunctional property descriptions targeted to support the selection of Web Services. The approach is based on the explicit distinction between NFP offered by providers and requested by users, on the concept of policy that aggregates NFP descriptions into single entities with an applicability condition, and finally on a set of constraint operators, which is particularly relevant for NFP requests. The semantic meta-model embracing the above perspective is defined by a BNF syntax whose semantics is formalized by an ontology. The ontology has been formalized in OWL-DL and WSML to provide for logical syntax. The logic upon which the meta-model supports NFP-based selection is discussed in the paper.

The discovery of a semantic web service (SWS) is the act of locating a machine-processable description of a SWS-related resource that may have been previously unknown and that meets certain functional criteria. The increasing availability of services that offer similar functionalities requires the discovery process to be enhanced with a selection phase that considers non-functional properties (NFPs) of services. This paper proposes a model to describe these properties and a novel approach to service selection. Our approach is based on the design of matching rules by means of mediators defined by sets of rules stating the condition for successful matches. These rules are based on the ontological description of objects representing NFPs that are required and offered. In particular, we define a set of rule schemas to support mediation and matching for a class of user-defined NFP-constraints clustered according to specified constraint operators. Rules support matching for both qualitative and quantitative non-functional properties.