Papers by Alan Ramponi

Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech Detection (2022.naacl-main)

Copied to clipboard

Challenge:	lexical biases in hate speech detection are limited when applied to real-world data, exhibiting limited out-of-distribution robustness and perpetuating harmful social biase.
Approach:	They propose to disentangle spurious and authentic artifacts and analyze their impact on out-of-distribution fairness and robustness.
Outcome:	The proposed models show that spurious artifacts require different treatments to attain robustness and fairness in hate speech detection.

Biomedical Event Extraction as Sequence Labeling (2020.emnlp-main)

Copied to clipboard

Alan Ramponi, Rob van der Goot, Rosario Lombardo, Barbara Plank

Information Extraction & Text Mining

Challenge:	Empirical results show that BeeSL’s speed and accuracy makes it a viable approach for large-scale real-world scenarios.
Approach:	They propose a joint end-to-end neural information extraction model that recasts the task as sequence labeling and jointly models intermediate tasks via multi-task learning.
Outcome:	Empirical results show that BeeSL outperforms the current best system on the Genia 2011 benchmark by 1.57% absolute F1 score reaching 60.22% F1 .

Fine-grained Fallacy Detection with Human Label Variation (2025.naacl-long)

Copied to clipboard

Alan Ramponi, Agnese Daffara, Sara Tonelli

Challenge:	Fallacy detection is an open challenge in NLP and has shown to be intrinsically difficult for both humans and machines.
Approach:	They propose a framework that minimizes annotation errors whilst keeping signals of human label variation.
Outcome:	The proposed framework minimizes annotation errors while keeping signals of human label variation.

Cross-Domain Evaluation of Edge Detection for Biomedical Event Extraction (2020.lrec-1)

Copied to clipboard

Alan Ramponi, Barbara Plank, Rosario Lombardo

Information Extraction & Text Mining

Challenge:	Biomedical event extraction systems are evaluated in-domain and on complete event structures only.
Approach:	They present a cross-domain study of edge detection for biomedical event extraction . they analyze differences between five existing gold standard corpora and provide a strong baseline model .
Outcome:	The proposed model shows a drop in performance when the baseline is applied on out-of-domain data.

Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP (2021.eacl-demos)

Copied to clipboard

Rob van der Goot, Ahmet Üstün, Alan Ramponi, Ibrahim Sharaf, Barbara Plank

Semantic Text Processing

Challenge:	Multi-task learning (MTL) has become a standard repertoire in natural language processing (NLP) it enables neural networks to learn tasks in parallel while leveraging the benefits of sharing parameters.
Approach:	They propose a toolkit for fine-tuning contextualized embeddings in multi-task settings.
Outcome:	The proposed toolkit supports a variety of natural language processing tasks . it enables neural networks to learn tasks in parallel while leveraging the benefits of sharing parameters.

Neural Unsupervised Domain Adaptation in NLP—A Survey (2020.coling-main)

Copied to clipboard

Alan Ramponi, Barbara Plank

Low-Resource NLP

Challenge:	Deep neural networks excel at learning from labeled data, but learning from unlabeled data remains a challenge.
Approach:	They review neural unsupervised domain adaptation techniques which do not require labeled target domain data.
Outcome:	The proposed techniques are more challenging yet widely applicable.

Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches (2025.emnlp-main)

Copied to clipboard

Alan Ramponi, Marco Rovera, Robert Moro, Sara Tonelli

Multilinguality

Challenge:	Previous work has mostly tackled the task monolingually, i.e., having both the input and the retrieved claims in the same language.
Approach:	They examine strategies to improve multilingual and crosslingual performance by selecting negative examples and re-ranking.
Outcome:	The proposed methods improve performance on a multilingual and crosslingual dataset.

Norm It! Lexical Normalization for Italian and Its Downstream Effects for Dependency Parsing (2020.lrec-1)

Copied to clipboard

Rob van der Goot, Alan Ramponi, Tommaso Caselli, Michele Cafagna, Lorenzo De Mattei

Syntactic Text Processing

Challenge:	Existing tools for lexical normalization of social media data are designed with canonical texts in mind, and this makes it difficult to process data in multiple languages.
Approach:	They propose to create a lexical normalization dataset for Italian and analyze the inter-annotator agreement for this task.
Outcome:	The proposed model improves the parsing of social media data in Italian and shows that it can be used to translate non-standard social media content to canonical language.

Translation in the Hands of Many: Centering Lay Users in Machine Translation Interactions (2025.emnlp-main)

Copied to clipboard

Beatrice Savoldi, Alan Ramponi, Matteo Negri, Luisa Bentivogli

Multilinguality

Challenge:	Multilingual demands and accessibility have made MT a global tool . however, the understanding of MT consumed by such a diverse group of users remains limited.
Approach:	They first trace the evolution of MT user profiles, focusing on non-experts and how their engagement with technology may shift with the rise of LLMs.
Outcome:	The proposed approach will help to align MT with user needs and improve the quality of the language.

Variationist: Exploring Multifaceted Variation and Bias in Written Language Data (2024.acl-demos)

Copied to clipboard

Alan Ramponi, Camilla Casula, Stefano Menini

Responsible & Trustworthy NLP

Challenge:	Existing tools that inspect and visualize language data are limited in their capabilities.
Approach:	They propose a highly-modular, extensible, and task-agnostic tool that inspects language variation and bias across multiple variables, language units, and diverse metrics.
Outcome:	The proposed tool can inspect and visualize language variation and bias across variables, language units, and diverse metrics that go beyond descriptive statistics.

From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding (2021.naacl-main)

Copied to clipboard

Rob van der Goot, Ibrahim Sharaf, Aizhan Imankulova, Ahmet Üstün, Marija Stepanović, Alan Ramponi, Siti Oryza Khairunnisa, Mamoru Komachi, Barbara Plank

Multilinguality

Challenge:	Lack of publicly available evaluation data for low-resource languages limits progress in SLU . despite advances in neural modeling for slot and intent detection, datasets for SLU remain limited.
Approach:	They propose a joint learning approach with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer.
Outcome:	The proposed model can learn English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer.

Delving into Qualitative Implications of Synthetic Data for Hate Speech Detection (2024.emnlp-main)

Copied to clipboard

Camilla Casula, Sebastiano Salto, Alan Ramponi, Sara Tonelli

Responsible & Trustworthy NLP

Challenge:	Recent work on synthetic data for training models for NLP tasks reports mixed results on subjective tasks such as hate speech detection.
Approach:	They propose to use synthetic data to train models for highly subjective tasks such as hate speech detection to investigate the potential and specific pitfalls of using it.
Outcome:	The proposed model outperforms models trained with real data on hate speech detection tasks, but it fails to accurately reflect real-world data on linguistic dimensions and results in different class distributions.