Papers by Simone Paolo Ponzetto

25 papers
Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect (2025.emnlp-main)

Copied to clipboard

Challenge: Prior work has focused largely on binary grammatical contrasts, but how do they encode their syntactic knowledge internally?
Approach: They propose to use a multidimensional hierarchical grammar phenomenon to identify distinct, orthogonal directions in residual space to demonstrate causal control over both grammatical features.
Outcome: The proposed model can encode tense and aspect in human-like ways, but effective steering during generation is sensitive to multiple factors and requires manual tuning or automated optimization.
Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers (2023.findings-eacl)

Copied to clipboard

Challenge: Existing studies show that incorporating demographic factors in language representations improves performance on downstream NLP tasks.
Approach: They use continuous language modeling and dynamic multi-task learning to adapt pre-trained Transformers to incorporate demographic information into their representations.
Outcome: The proposed model shows that the results are consistent with previous studies.
Our kind of people? Detecting populist references in political debates (2023.findings-eacl)

Copied to clipboard

Challenge: Existing literature on populism has only limited agreement on its exact properties .
Approach: They propose a cross-lingual dataset to identify populist rhetoric in text . they propose 'hierarchical' annotation procedure to annotate populist references .
Outcome: The proposed dataset can be used to investigate how political actors talk about The Elite and The People and to study how populist rhetoric is used as a strategic device.
Out of the Mouths of MPs: Speaker Attribution in Parliamentary Debates (2024.lrec-main)

Copied to clipboard

Challenge: Identifying who says what to whom is an essential prerequisite for analysing human communication.
Approach: They propose a new corpus for speaker attribution in german parliamentary debates . the data includes more than 7,700 manually annotated events of speech, thought and writing . they then apply their model to predict speech events in 20 years of debates and investigate the use of factives in the rhetoric of MPs.
Outcome: The proposed model predicts speech events in 20 years of debates and investigates the use of factives in the rhetoric of MPs.
SEAGLE: A Platform for Comparative Evaluation of Semantic Encoders for Information Retrieval (D19-3)

Copied to clipboard

Challenge: Existing semantic text encoding models are limited in coverage and few attempts to empirically compare them on IR tasks have been made.
Approach: They propose to implement word embedding aggregators and pretrained semantic encoders and to allow for their comparative evaluation on arbitrary IR collections.
Outcome: The proposed model can be exploited via an easy-to-use web interface and its modular backend (micro-service architecture) can easily be extended with additional semantic search models.
FakeFlow: Fake News Detection by Modeling the Flow of Affective Information (2021.eacl-main)

Copied to clipboard

Challenge: In short news articles, authors add exaggerations or fabricate events to manipulate readers' emotions.
Approach: They propose to model the flow of affective information in fake news articles using a neural architecture and combine topic and affective data extracted from text.
Outcome: The proposed model outperforms state-of-the-art methods on four real-world datasets and shows that it can capture the flow of affective information in fake news articles.
BABELEDITS: A Benchmark and a Modular Approach for Robust Cross-lingual Knowledge Editing of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for cross-lingual knowledge editing are limited in their effectiveness and robustness.
Approach: They propose a new CKE benchmark that accounts for the rich variety of entity aliases within and across languages.
Outcome: The proposed method is more effective than state-of-the-art methods and robust against model collapse when subjected to multiple edits.
Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translation (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly used for creative tasks such as literary translation.
Approach: They propose a paired-task framework that assesses translational creativity using Units of Creative Potential (UCPs) they benchmark 23 models and four creativity-oriented prompts to assess translational comprehension .
Outcome: The proposed framework compares 23 models and four creativity-oriented prompts on literary excerpts from 11 books.
Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies on text embeddings focus less on how information is encoded.
Approach: They find that truncating embedding dimensions causes an increase in performance when removed.
Outcome: The proposed method improves performance across 6 state-of-the-art text encoders and 26 downstream tasks.
Investigating the Role of Argumentation in the Rhetorical Analysis of Scientific Publications with Neural Multi-Task Learning Models (D18-1)

Copied to clipboard

Challenge: Scientific publications are argumentative and often adhere to well-trodden rhetorical patterns and argumentation schemes.
Approach: They investigate the link between scientific publications and rhetorical aspects such as discourse categories or citation contexts by coupling rhetorical classifiers with extraction of argumentative components.
Outcome: The proposed models show significant performance gains for different rhetorical analysis tasks.
How to Do Politics with Words: Investigating Speech Acts in Parliamentary Debates (2024.lrec-main)

Copied to clipboard

Challenge: a new perspective on framing through the lens of speech acts investigates how politicians make use of different pragmatic speech act functions in political debates.
Approach: They propose a new framework for framing through the lens of speech acts and an annotation scheme for political debates.
Outcome: The proposed framework can predict speech acts with an avg. F1 of around 82.0% . the proposed framework is based on a dataset of German parliamentary debates .
CATS: A Tool for Customized Alignment of Text Simplification Corpora (L18-1)

Copied to clipboard

Challenge: Existing corpora of original sentences and their manual simplifications are very scarce and small in size, hindering automated text simplification systems.
Approach: They propose a language-independent tool for sentence alignment from parallel/comparable TS resources.
Outcome: The proposed tool performs well on English and Spanish corpora and compares sentences based on their semantic overlap.
Come hither or go away? Recognising pre-electoral coalition signals in the news (2021.emnlp-main)

Copied to clipboard

Challenge: In this paper, we decompose the task of recognizing from the news coverage leading up to an election the (un)willingness of political parties to form a coalition into two related, but distinct tasks.
Approach: They propose a task of recognizing from news coverage the (un)willingness of political parties to form a coalition from text and a sub-task of predicting the polarity of the signal.
Outcome: The proposed approach improves over a strong monolingual transfer learning baseline.
Massively Multilingual Lexical Specialization of Multilingual Transformers (2023.acl-long)

Copied to clipboard

Challenge: Existing work focused on lexical specialization of monolingual PLMs with immense quantities of monolinguistic constraints, but recent work shows that pretrained language models can be rewired to produce high-quality word representations and perform type-level lexicals.
Approach: They propose to expose massively multilingual transformers to multilingual lexical knowledge at scale using BabelNet as a source of multilingual and cross-lingual type-level lexicon knowledge.
Outcome: The proposed method shows that pretrained language models can be rewired to produce high-quality word representations and perform type-level lexical tasks.
GenGO Ultra: an LLM-powered ACL Paper Explorer (2025.acl-demo)

Copied to clipboard

Challenge: The main repository of natural language processing (NLP) has grown its number of stored papers by 70% from 2019 to 2023.
Approach: They propose an extension to GenGO Ultra which exploits large language models to dynamically generate responses grounded by published papers.
Outcome: The proposed system exploits large language models to generate responses grounded by published papers and performs multi-granularity experiments.
Computational Analysis of Political Texts: Bridging Research Efforts Across Communities (P19-4)

Copied to clipboard

Challenge: Political scientists have developed and adopted natural language processing (NLP) methods to exploit text as an additional source of data in their analyses.
Approach: This tutorial aims to provide a gentle introduction to methods and tasks related to computational analysis of political texts from both communities.
Outcome: The main goal of this tutorial is to bring the two research communities closer to each other and contribute to faster and more significant developments in this interdisciplinary area.
The Robotic Surgery Procedural Framebank (2022.lrec-1)

Copied to clipboard

Challenge: Surgical practice has steadily improved thanks to the support of the approaches made available by observational science.
Approach: They propose to extract from robot-surgical texts verbs and nouns that describe surgical actions and extend PropBank frames by adding any of new lemmas, frames or role sets required to cover missing lemae.
Outcome: The proposed resource can be used to train and evaluate Semantic Role Labeling (SRL) systems in a fine-grained domain setting.
Enriching Frame Representations with Distributionally Induced Senses (L18-1)

Copied to clipboard

Challenge: lexical resource that enriches Framester knowledge graph with semantic features from text corpora . paves way for development of novel, deeper semantic-aware applications .
Approach: They propose a lexical resource that enriches the Framester knowledge graph with semantic features from text corpora.
Outcome: The proposed resource enables the development of deeper semantic-aware applications . it combines knowledge from text and symbolic representations of events and participants .
MIsA: Multilingual “IsA” Extraction from Corpora (L18-1)

Copied to clipboard

Challenge: In this paper, we present a collection of hypernymy relations extracted from the Wikipedia corpus in five languages.
Approach: They present a collection of hypernymy relations extracted from the Wikipedia corpus in five languages . they use existing or newly defined lexico-syntactic patterns to extract hyperniyms .
Outcome: The proposed tool is based on a dictionary extracted from the full Wikipedia corpus.
DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces (2021.eacl-demos)

Copied to clipboard

Challenge: Recent research has shown that distributional word vector spaces often encode stereotypical human biases, such as racism and sexism.
Approach: They propose a platform that measures and mitigates bias in word embeddings by executing two (mutually composable) debiasing models.
Outcome: The proposed platform can measure and mitiga bias in word embeddings.
Moral Framing in Politics (MFiP): A new resource and models for moral framing (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on detecting moral values in political communication, trying to identify moral frames used by political actors or parties to convey their messages.
Approach: They propose to code German parliamentary debates to identify moral framing and to detect subtle differences in politicians’ moral framming.
Outcome: The proposed model distinguishes between different types of moral frames and includes narrative roles, together with the moral foundations for each frame.
Unsupervised Semantic Frame Induction using Triclustering (P18-2)

Copied to clipboard

Challenge: Recent work on frame-semantics has enabled the development of wide-coverage frame parsers using supervised learning.
Approach: They propose to use dependency triples to perform unsupervised frame induction on a Web-scale corpus.
Outcome: The proposed approach performs state-of-the-art on a FrameNet-derived dataset and performs on par with competitive methods on . verb class clustering task.
Multilingual and Cross-Lingual Graded Lexical Entailment (P19-1)

Copied to clipboard

Challenge: a novel method for capturing graded (and binary) LE is developed for cross-lingual generalisation of lexical entailment . lexicale enlargement is a key principle behind hierarchical structure found in semantic networks .
Approach: They propose a method for cross-lingual generalisation of GR-LE relation using hyperlex and a bilingual dictionary.
Outcome: The proposed method outperforms current state-of-the-art on binary cross-lingual LE detection by a wide margin.
An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages (L18-1)

Copied to clipboard

Challenge: Existing systems for word sense disambiguation are limited to the Russian language and lack of resources to address the problem.
Approach: They propose an unsupervised system for word sense disambiguation that uses a traditional vector space model to estimate the most similar word sense corresponding to its context.
Outcome: The proposed system outperforms the sparse mode on all datasets according to the adjusted Rand index.
Word Sense Disambiguation for 158 Languages using Word Embeddings Only (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods of disambiguation of word senses are based on knowledge bases, taxonomies, and other externally built resources.
Approach: They propose a method that takes a pre-trained word embedding model and induces a fully-fledged word sense inventory for 158 languages.
Outcome: The proposed model is based on a pre-trained word embedding model and induces a fully-fledged word sense inventory in 158 languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations