Papers by Elena Cabrio

18 papers
Argument-based Detection and Classification of Fallacies in Political Debates (2023.emnlp-main)

Copied to clipboard

Challenge: Fallacies are arguments that employ faulty reasoning, causing inaccurate conclusions and invalid inferences . ad hominem fallacy is one of the most common fallacy labels used in political debates despite its use in many scenarios .
Approach: They extend the ElecDeb60To16 dataset of U.S. presidential debates annotated with fallacious arguments by incorporating the most recent Trump-Biden debate.
Outcome: The proposed method extends the ElecDeb60To16 dataset of U.S. presidential debates annotated with fallacious arguments .
MedMT5: An Open-Source Multilingual Text-to-Text LLM for the Medical Domain (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on large language models for medical applications have focused on a single language . medical mT5 outperforms both encoders and similar sized text-to-text models in English, French, and Italian benchmarks .
Approach: They propose to train Medical mT5, the first open-source text-to-text multilingual model for the medical domain.
Outcome: The proposed model outperforms encoders and similar sized models on the Spanish, French, and Italian benchmarks while being competitive with current state-of-the-art models in English.
Stakeholder Suite: A Unified AI Framework for Mapping Actors, Topics and Arguments in Public Debates (2026.eacl-demo)

Copied to clipboard

Challenge: Existing media intelligence tools rely on descriptive analytics with limited transparency.
Approach: They propose a framework for mapping actors, topics, and arguments within public debates . it combines actor detection, topic modeling, argument extraction and stance classification . the framework is tested on multiple energy infrastructure projects as a case study .
Outcome: The proposed framework delivers fine-grained, source-grounded insights while remaining adaptable to diverse domains.
AM4DSP: Argumentation Mining in Structured Decentralized Discussion Platforms for Deliberative Democracy (2025.emnlp-demos)

Copied to clipboard

Challenge: Argument mining is the automated process of identification and extraction of argumentative structures in natural language.
Approach: They propose to use argument mining to extract arguments from online discussions in the context of deliberative democracy.
Outcome: The proposed system enables the extraction and analysis of arguments from online discussions in the context of deliberative democracy.
Argument Quality Assessment in the Age of Instruction-Following Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Argument quality assessment is critical for opinion formation, decision making, writing education, and the like.
Approach: They propose to use large language models to leverage knowledge across contexts to enable a much more reliable assessment.
Outcome: The proposed approach improves the quality of argumentation and the ability to leverage knowledge across contexts.
Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have demonstrated the effectiveness of cross-lingual language model pre-training on NLP tasks.
Approach: They propose a hybrid emoji-based Masked Language Model to leverage eojis across languages to improve the learning of short text messages.
Outcome: The proposed model performs better on German, Italian and Spanish.
Graph Embeddings for Argumentation Quality Assessment (2022.findings-emnlp)

Copied to clipboard

Challenge: Argumentation is the process by which arguments are constructed, compared, evaluated in several respects and judged in order to establish whether any of them is warranted.
Approach: They propose to annotate 1908 arguments tagged with quality facets from a resource of 402 persuasive essays and to use them to create a neural architecture that takes into account the support and attack relations holding among the arguments.
Outcome: The proposed neural architecture outperforms state-of-the-art and standard arguments on the persuasive essays dataset.
An In-depth Analysis of Implicit and Subtle Hate Speech Messages (2023.eacl-main)

Copied to clipboard

Challenge: Explicit hate speech is more easily identifiable by recognizing hateful words, but subtle messages are harmful . subtle messages contain linguistically subtle and implicit forms of HS, such as circumlocution, metaphors and sarcasm . social media have faced pressure from civil rights groups demanding to monitor and limit online hate speech .
Approach: They propose to use a fine-grained definition of implicit and subtle messages to detect HS . they then experiment with neural network architectures to detect subtle content .
Outcome: The proposed models perform satisfactory on explicit messages, but fail to detect subtle content.
DISPUTool 3.0: Fallacy Detection and Repairing in Argumentative Political Debates (2025.acl-demo)

Copied to clipboard

Challenge: DISPUTool 3.0 is a web-based application for identifying and fixing fallacious arguments in political debates.
Approach: They propose a web-based application designed to identify and repair fallacious arguments in political debates.
Outcome: The proposed tool is based on the ElecDeb60to20 dataset covering US presidential debates from 1960 to 2020.
CyberAgressionAdo-v1: a Dataset of Annotated Online Aggressions in French Collected through a Role-playing Game (2022.lrec-1)

Copied to clipboard

Challenge: Recent studies have highlighted that private instant messaging platforms are major mediums of cyber aggression among teens.
Approach: They present a dataset of aggressive chats in French collected through a role-playing game in high-schools . they provide insights on the different types of aggression and verbal abuse depending on the targeted victims .
Outcome: The proposed dataset analyzes aggressive conversations in French on a role-playing game in high schools . it provides insights on the different types of aggression and verbal abuse depending on the targeted victims .
Regrexit or not Regrexit: Aspect-based Sentiment Analysis in Polarized Contexts (2020.coling-main)

Copied to clipboard

Challenge: Aspect-based Sentiment Analysis (ABSA) aims at capturing sentiment expressed toward each aspect of a target entity.
Approach: They propose to extend the task of Aspect-based Sentiment Analysis (ABSA) toward affect and emotion representation in polarized settings.
Outcome: The proposed model captures aspect-based polarization from newspapers regarding the Brexit scenario of 1.2m entities at sentence-level.
Playing the Part of the Sharp Bully: Generating Adversarial Examples for Implicit Hate Speech Detection (2023.findings-acl)

Copied to clipboard

Challenge: Existing algorithms for hate speech detection focus on explicit forms of hate speech, but they fail to properly detect subtle and implicit HS messages.
Approach: They propose a framework for generating adversarial implicit HS short-text messages using Auto-regressive language models and a strategy to group the generated messages in complexity levels.
Outcome: The proposed framework shows that iteratively retraining on HARD messages significantly improves implicit HS benchmarks.
Yes, we can! Mining Arguments in 50 Years of US Presidential Campaign Debates (P19-1)

Copied to clipboard

Challenge: Political debates are a natural application scenario for Argument Mining.
Approach: They propose an argument mining approach to political debates that uses argument components to annotate 39 political debate from the last 50 years of US presidential campaigns.
Outcome: The proposed approach outperforms baselines in argument mining over political debates.
CasiMedicos-Arg: A Medical Question Answering Dataset Annotated with Explanatory Argumentative Structures (2024.emnlp-main)

Copied to clipboard

Challenge: Existing tools to aid residents in teaching medical doctors to explain decisions are a key objective of AI in education.
Approach: They present a multilingual dataset for Medical Question Answering where doctors can annotate correct and incorrect diagnoses with argument components and argument relations.
Outcome: The proposed dataset consists of 558 clinical cases with explanations in English, Spanish, French, Italian and annotated with argument components and argument relations.
Love Me, Love Me, Say (and Write!) that You Love Me: Enriching the WASABI Song Corpus with Lyrics Annotations (2020.lrec-1)

Copied to clipboard

Challenge: a corpus of songs enriched with metadata extracted from music databases on the Web contains 1.73M songs with lyrics (1.41M unique lyrics) a researcher proposes methods to extract relevant information from lyrics, including their structure segmentation, topic, explicitness of lyrics content, salient passages of a song and emotions conveyed.
Approach: They propose to extract relevant information from lyrics by using music databases . they propose to use metadata extracted from music databases to analyze lyrics .
Outcome: The proposed methods can be exploited by music search engines and music professionals to better handle large collections of lyrics.
Lyrics Segmentation: Textual Macrostructure Detection using Convolutions (C18-1)

Copied to clipboard

Challenge: Lyrics contain repeated patterns that are correlated with the repetitions found in the music they accompany.
Approach: They propose to apply a convolutional neural network to a task to detect lyrics by using a neural network.
Outcome: The proposed features improve the state-of-the-art in lyrics segmentation . a convolutional neural network is applied to the task and it is able to detect lyrics in different genres.
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering (2024.emnlp-main)

Copied to clipboard

Challenge: Automated responses lack argumentative richness which characterises expert-produced counterspeech.
Approach: They propose to automate counterspeech generation by investigating tension between helpfulness and harmlessness of LLMs and to assess whether presence of safety guardrails hinders quality of generations.
Outcome: The proposed approach produces more cogent responses that lack argumentative richness which characterises expert-produced counterspeech.
Unmasking the Hidden Meaning: Bridging Implicit and Explicit Hate Speech Embedding Representations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to detect explicit hate speech (HS) are focusing on detecting explicit forms of hateful expressions on user-generated content.
Approach: They propose to examine the differences between embedding implicit and explicit hateful messages . they compare and link explicit and implicit hateful message across datasets .
Outcome: The proposed model improves on explicit hate speech detection while retaining high performance on borderline cases.

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