Enrico Santus

Simone Scaboro, Beatrice Portelli, Emmanuele Chersoni et al.

In the last decade, an increasing number of users have started reporting Adverse Drug Events (ADE) on social media platforms, blogs, and health forums. Given the large volume of reports, pharmacovigilance has focused on ways to use Natural Language Processing (NLP) techniques to rapidly examine these large collections of text, detecting mentions of drug-related adverse reactions to trigger medical investigations. However, despite the growing interest in the task and the advances in NLP, the robustness of these models in face of linguistic phenomena such as negations and speculations is an open research question. Negations and speculations are pervasive phenomena in natural language, and can severely hamper the ability of an automated system to discriminate between factual and nonfactual statements in text. In this paper we take into consideration four state-of-the-art systems for ADE detection on social media texts. We introduce SNAX, a benchmark to test their performance against samples containing negated and speculated ADEs, showing their fragility against these phenomena. We then introduce two possible strategies to increase the robustness of these models, showing that both of them bring significant increases in performance, lowering the number of spurious entities predicted by the models by 60% for negation and 80% for speculations.

Simone Scaboro, Beatrice Portellia, Emmanuele Chersoni et al.

Adverse Event (ADE) extraction is one of the core tasks in digital pharmacovigilance, especially when applied to informal texts. This task has been addressed by the Natural Language Processing community using large pre-trained language models, such as BERT. Despite the great number of Transformer-based architectures used in the literature, it is unclear which of them has better performances and why. Therefore, in this paper we perform an extensive evaluation and analysis of 19 Transformer-based models for ADE extraction on informal texts. We compare the performance of all the considered models on two datasets with increasing levels of informality (forums posts and tweets). We also combine the purely Transformer-based models with two commonly-used additional processing layers (CRF and LSTM), and analyze their effect on the models performance. Furthermore, we use a well-established feature importance technique (SHAP) to correlate the performance of the models with a set of features that describe them: model category (AutoEncoding, AutoRegressive, Text-to-Text), pretraining domain, training from scratch, and model size in number of parameters. At the end of our analyses, we identify a list of take-home messages that can be derived from the experimental data.

Beatrice Portelli, Simone Scaboro, Enrico Santus et al.

Medical term normalization consists in mapping a piece of text to a large number of output classes. Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts. An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models. The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.

Beatrice Portelli, Simone Scaboro, Emmanuele Chersoni et al.

This paper describes the models developed by the AILAB-Udine team for the SMM4H 22 Shared Task. We explored the limits of Transformer based models on text classification, entity extraction and entity normalization, tackling Tasks 1, 2, 5, 6 and 10. The main take-aways we got from participating in different tasks are: the overwhelming positive effects of combining different architectures when using ensemble learning, and the great potential of generative models for term normalization.

Parisa Kordjamshidi, Samer Aslan, Madhavan Seshadri et al.

Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reasoning ability or artifacts of data contamination. We present a comprehensive empirical study of tax law reasoning approaches and implement a contamination detection protocol to rigorously assess LLM reliability. We show that performance can be inflated by contamination. Building on this analysis, we conduct a systematic evaluation, comparing monolithic LLMs with hybrid systems that translate statutory text into formal representations and delegate inference to symbolic solvers. We build a novel test suite designed to probe generalization to unseen documents via case and rule variations. Our findings indicate that legal reasoning is inherently compositional and that neuro-symbolic frameworks offer a more reliable and robust foundation for legal AI, as well as improved generalization to unobserved situations.

Hooman Sedghamiz, Shivam Raval, Enrico Santus et al.

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving sequence representations. This paper introduces SupCL-Seq, which extends the supervised contrastive learning from computer vision to the optimization of sequence representations in NLP. By altering the dropout mask probability in standard Transformer architectures, for every representation (anchor), we generate augmented altered views. A supervised contrastive loss is then utilized to maximize the system's capability of pulling together similar samples (e.g., anchors and their altered views) and pushing apart the samples belonging to the other classes. Despite its simplicity, SupCLSeq leads to large gains in many sequence classification tasks on the GLUE benchmark compared to a standard BERTbase, including 6% absolute improvement on CoLA, 5.4% on MRPC, 4.7% on RTE and 2.6% on STSB. We also show consistent gains over self supervised contrastively learned representations, especially in non-semantic tasks. Finally we show that these gains are not solely due to augmentation, but rather to a downstream optimized sequence representation. Code: https://github.com/hooman650/SupCL-Seq

Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan et al.

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data.

Paolo Pedinotti, Peter Baumann, Nathan Jessurun et al.

Large Language Models (LLMs) have rapidly reshaped financial NLP, enabling new tasks and driving a proliferation of datasets and diversification of data sources. Yet, this transformation has outpaced traditional surveys. In this paper, we present MetaGraph, a generalizable methodology for extracting knowledge graphs from scientific literature and analyzing them to obtain a structured, queryable view of research trends. We define an ontology for financial NLP research and apply an LLM-based extraction pipeline to 681 papers (2022-2025), enabling large-scale, data-driven analysis. MetaGraph reveals three key phases: early LLM adoption and task/dataset innovation; critical reflection on LLM limitations; and growing integration of peripheral techniques into modular systems. This structured view offers both practitioners and researchers a clear understanding of how financial NLP has evolved - highlighting emerging trends, shifting priorities, and methodological shifts-while also demonstrating a reusable approach for mapping scientific progress in other domains.

Simone Scaboro, Beatrice Portelli, Emmanuele Chersoni et al.

Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations. However, despite the recent advances in NLP, it is currently unknown if such models are robust in face of negation, which is pervasive across language varieties. In this paper we evaluate three state-of-the-art systems, showing their fragility against negation, and then we introduce two possible strategies to increase the robustness of these models: a pipeline approach, relying on a specific component for negation detection; an augmentation of an ADE extraction dataset to artificially create negated samples and further train the models. We show that both strategies bring significant increases in performance, lowering the number of spurious entities predicted by the models. Our dataset and code will be publicly released to encourage research on the topic.

Shivam Raval, Hooman Sedghamiz, Enrico Santus et al.

Adverse Events (AE) are harmful events resulting from the use of medical products. Although social media may be crucial for early AE detection, the sheer scale of this data makes it logistically intractable to analyze using human agents, with NLP representing the only low-cost and scalable alternative. In this paper, we frame AE Detection and Extraction as a sequence-to-sequence problem using the T5 model architecture and achieve strong performance improvements over competitive baselines on several English benchmarks (F1 = 0.71, 12.7% relative improvement for AE Detection; Strict F1 = 0.713, 12.4% relative improvement for AE Extraction). Motivated by the strong commonalities between AE-related tasks, the class imbalance in AE benchmarks and the linguistic and structural variety typical of social media posts, we propose a new strategy for multi-task training that accounts, at the same time, for task and dataset characteristics. Our multi-task approach increases model robustness, leading to further performance gains. Finally, our framework shows some language transfer capabilities, obtaining higher performance than Multilingual BERT in zero-shot learning on French data.

Paolo Pedinotti, Giulia Rambelli, Emmanuele Chersoni et al.

Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation between verbs and arguments in isolation, in this paper we take a broader perspective by assessing whether and to what extent computational approaches have access to the information about the typicality of entire events and situations described in language (Generalized Event Knowledge). Given the recent success of Transformers Language Models (TLMs), we decided to test them on a benchmark for the \textit{dynamic estimation of thematic fit}. The evaluation of these models was performed in comparison with SDM, a framework specifically designed to integrate events in sentence meaning representations, and we conducted a detailed error analysis to investigate which factors affect their behavior. Our results show that TLMs can reach performances that are comparable to those achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge, and their predictions often depend on surface linguistic features, such as frequent words, collocations and syntactic patterns, thereby showing sub-optimal generalization abilities.

Beatrice Portelli, Daniele Passabì, Edoardo Lenzi et al.

In recent years, Internet users are reporting Adverse Drug Events (ADE) on social media, blogs and health forums. Because of the large volume of reports, pharmacovigilance is seeking to resort to NLP to monitor these outlets. We propose for the first time the use of the SpanBERT architecture for the task of ADE extraction: this new version of the popular BERT transformer showed improved capabilities with multi-token text spans. We validate our hypothesis with experiments on two datasets (SMM4H and CADEC) with different text typologies (tweets and blog posts), finding that SpanBERT combined with a CRF outperforms all the competitors on both of them.

Jiaming Luo, Frederik Hartmann, Enrico Santus et al.

Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship.

Tal Schuster, Darsh J Shah, Yun Jie Serene Yeo et al.

Fact verification requires validating a claim in the context of evidence. We show, however, that in the popular FEVER dataset this might not necessarily be the case. Claim-only classifiers perform competitively with top evidence-aware models. In this paper, we investigate the cause of this phenomenon, identifying strong cues for predicting labels solely based on the claim, without considering any evidence. We create an evaluation set that avoids those idiosyncrasies. The performance of FEVER-trained models significantly drops when evaluated on this test set. Therefore, we introduce a regularization method which alleviates the effect of bias in the training data, obtaining improvements on the newly created test set. This work is a step towards a more sound evaluation of reasoning capabilities in fact verification models.

Emmanuele Chersoni, Enrico Santus, Ludovica Pannitto et al.

Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a Structured Distributional Model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal structure derived from Discourse Representation Theory and containing distributional vectors. This structure is dynamically and incrementally built by integrating knowledge about events and their typical participants, as they are activated by lexical items. Event knowledge is modeled as a graph extracted from parsed corpora and encoding roles and relationships between participants that are represented as distributional vectors. SDM is grounded on extensive psycholinguistic research showing that generalized knowledge about events stored in semantic memory plays a key role in sentence comprehension. We evaluate SDM on two recently introduced compositionality datasets, and our results show that combining a simple compositional model with event knowledge constantly improves performances, even with different types of word embeddings.

Zhijing Jin, Di Jin, Jonas Mueller et al.

Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel data. Existing approaches try to explicitly disentangle content and attribute information, but this is difficult and often results in poor content-preservation and ungrammaticality. In contrast, we propose a simpler approach, Iterative Matching and Translation (IMaT), which: (1) constructs a pseudo-parallel corpus by aligning a subset of semantically similar sentences from the source and the target corpora; (2) applies a standard sequence-to-sequence model to learn the attribute transfer; (3) iteratively improves the learned transfer function by refining imperfections in the alignment. In sentiment modification and formality transfer tasks, our method outperforms complex state-of-the-art systems by a large margin. As an auxiliary contribution, we produce a publicly-available test set with human-generated transfer references.

Yujie Qian, Enrico Santus, Zhijing Jin et al.

Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies. Non-local and non-sequential context is, however, a valuable source of information to improve predictions. In this paper, we introduce GraphIE, a framework that operates over a graph representing a broad set of dependencies between textual units (i.e. words or sentences). The algorithm propagates information between connected nodes through graph convolutions, generating a richer representation that can be exploited to improve word-level predictions. Evaluation on three different tasks --- namely textual, social media and visual information extraction --- shows that GraphIE consistently outperforms the state-of-the-art sequence tagging model by a significant margin.

Enrico Santus, Hongmin Wang, Emmanuele Chersoni et al.

Word Embeddings have recently imposed themselves as a standard for representing word meaning in NLP. Semantic similarity between word pairs has become the most common evaluation benchmark for these representations, with vector cosine being typically used as the only similarity metric. In this paper, we report experiments with a rank-based metric for WE, which performs comparably to vector cosine in similarity estimation and outperforms it in the recently-introduced and challenging task of outlier detection, thus suggesting that rank-based measures can improve clustering quality.

Enrico Santus, Chris Biemann, Emmanuele Chersoni

This paper describes BomJi, a supervised system for capturing discriminative attributes in word pairs (e.g. yellow as discriminative for banana over watermelon). The system relies on an XGB classifier trained on carefully engineered graph-, pattern- and word embedding based features. It participated in the SemEval- 2018 Task 10 on Capturing Discriminative Attributes, achieving an F1 score of 0:73 and ranking 2nd out of 26 participant systems.

Emmanuele Chersoni, Enrico Santus, Philippe Blache et al.

Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The few exceptions have mostly modeled this phenomenon with structured distributional models, implicitly assuming a similarly structured representation of events. Recent experimental evidence, however, suggests that human processing system could also exploit an unstructured "bag-of-arguments" type of event representation to predict upcoming input. In this paper, we re-implement a traditional structured model and adapt it to compare the different hypotheses concerning the degree of structure in our event knowledge, evaluating their relative performance in the task of the argument expectations update.

Enrico Santus, Emmanuele Chersoni, Alessandro Lenci et al.

In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), and then we compute thematic fit as a weighted overlap between the top features of candidate fillers and role prototypes. Our experiments show that our method consistently outperforms a baseline re-implementing a state-of-the-art system, and achieves better or comparable results to those reported in the literature for the other unsupervised systems. Moreover, it provides an explicit representation of the features characterizing verb-specific semantic roles.

Dominik Schlechtweg, Stefanie Eckmann, Enrico Santus et al.

This paper explores the information-theoretic measure entropy to detect metaphoric change, transferring ideas from hypernym detection to research on language change. We also build the first diachronic test set for German as a standard for metaphoric change annotation. Our model shows high performance, is unsupervised, language-independent and generalizable to other processes of semantic change.

Vered Shwartz, Enrico Santus, Dominik Schlechtweg

The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution. We investigate an extensive number of such unsupervised measures, using several distributional semantic models that differ by context type and feature weighting. We analyze the performance of the different methods based on their linguistic motivation. Comparison to the state-of-the-art supervised methods shows that while supervised methods generally outperform the unsupervised ones, the former are sensitive to the distribution of training instances, hurting their reliability. Being based on general linguistic hypotheses and independent from training data, unsupervised measures are more robust, and therefore are still useful artillery for hypernymy detection.

Emmanuele Chersoni, Giulia Rambelli, Enrico Santus

In this paper, we describe ROOT 18, a classifier using the scores of several unsupervised distributional measures as features to discriminate between semantically related and unrelated words, and then to classify the related pairs according to their semantic relation (i.e. synonymy, antonymy, hypernymy, part-whole meronymy). Our classifier participated in the CogALex-V Shared Task, showing a solid performance on the first subtask, but a poor performance on the second subtask. The low scores reported on the second subtask suggest that distributional measures are not sufficient to discriminate between multiple semantic relations at once.

Enrico Santus, Emmanuele Chersoni, Alessandro Lenci et al.

In Distributional Semantic Models (DSMs), Vector Cosine is widely used to estimate similarity between word vectors, although this measure was noticed to suffer from several shortcomings. The recent literature has proposed other methods which attempt to mitigate such biases. In this paper, we intend to investigate APSyn, a measure that computes the extent of the intersection between the most associated contexts of two target words, weighting it by context relevance. We evaluated this metric in a similarity estimation task on several popular test sets, and our results show that APSyn is in fact highly competitive, even with respect to the results reported in the literature for word embeddings. On top of it, APSyn addresses some of the weaknesses of Vector Cosine, performing well also on genuine similarity estimation.

Emmanuele Chersoni, Enrico Santus, Alessandro Lenci et al.

Several studies on sentence processing suggest that the mental lexicon keeps track of the mutual expectations between words. Current DSMs, however, represent context words as separate features, thereby loosing important information for word expectations, such as word interrelations. In this paper, we present a DSM that addresses this issue by defining verb contexts as joint syntactic dependencies. We test our representation in a verb similarity task on two datasets, showing that joint contexts achieve performances comparable to single dependencies or even better. Moreover, they are able to overcome the data sparsity problem of joint feature spaces, in spite of the limited size of our training corpus.

Enrico Santus, Tin-Shing Chiu, Qin Lu et al.

In this paper, we claim that vector cosine, which is generally considered among the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by an unsupervised measure that calculates the extent of the intersection among the most mutually dependent contexts of the target words. To prove it, we describe and evaluate APSyn, a variant of the Average Precision that, without any optimization, outperforms the vector cosine and the co-occurrence on the standard ESL test set, with an improvement ranging between +9.00% and +17.98%, depending on the number of chosen top contexts.

Enrico Santus, Tin-Shing Chiu, Qin Lu et al.

In this paper, we describe ROOT13, a supervised system for the classification of hypernyms, co-hyponyms and random words. The system relies on a Random Forest algorithm and 13 unsupervised corpus-based features. We evaluate it with a 10-fold cross validation on 9,600 pairs, equally distributed among the three classes and involving several Parts-Of-Speech (i.e. adjectives, nouns and verbs). When all the classes are present, ROOT13 achieves an F1 score of 88.3%, against a baseline of 57.6% (vector cosine). When the classification is binary, ROOT13 achieves the following results: hypernyms-co-hyponyms (93.4% vs. 60.2%), hypernymsrandom (92.3% vs. 65.5%) and co-hyponyms-random (97.3% vs. 81.5%). Our results are competitive with stateof-the-art models.

Enrico Santus, Alessandro Lenci, Tin-Shing Chiu et al.

ROOT9 is a supervised system for the classification of hypernyms, co-hyponyms and random words that is derived from the already introduced ROOT13 (Santus et al., 2016). It relies on a Random Forest algorithm and nine unsupervised corpus-based features. We evaluate it with a 10-fold cross validation on 9,600 pairs, equally distributed among the three classes and involving several Parts-Of-Speech (i.e. adjectives, nouns and verbs). When all the classes are present, ROOT9 achieves an F1 score of 90.7%, against a baseline of 57.2% (vector cosine). When the classification is binary, ROOT9 achieves the following results against the baseline: hypernyms-co-hyponyms 95.7% vs. 69.8%, hypernyms-random 91.8% vs. 64.1% and co-hyponyms-random 97.8% vs. 79.4%. In order to compare the performance with the state-of-the-art, we have also evaluated ROOT9 in subsets of the Weeds et al. (2014) datasets, proving that it is in fact competitive. Finally, we investigated whether the system learns the semantic relation or it simply learns the prototypical hypernyms, as claimed by Levy et al. (2015). The second possibility seems to be the most likely, even though ROOT9 can be trained on negative examples (i.e., switched hypernyms) to drastically reduce this bias.

Enrico Santus, Tin-Shing Chiu, Qin Lu et al.

In this paper, we claim that Vector Cosine, which is generally considered one of the most efficient unsupervised measures for identifying word similarity in Vector Space Models, can be outperformed by a completely unsupervised measure that evaluates the extent of the intersection among the most associated contexts of two target words, weighting such intersection according to the rank of the shared contexts in the dependency ranked lists. This claim comes from the hypothesis that similar words do not simply occur in similar contexts, but they share a larger portion of their most relevant contexts compared to other related words. To prove it, we describe and evaluate APSyn, a variant of Average Precision that, independently of the adopted parameters, outperforms the Vector Cosine and the co-occurrence on the ESL and TOEFL test sets. In the best setting, APSyn reaches 0.73 accuracy on the ESL dataset and 0.70 accuracy in the TOEFL dataset, beating therefore the non-English US college applicants (whose average, as reported in the literature, is 64.50%) and several state-of-the-art approaches.