Evaluation of LLMs in context of Evidence-based Claim verification to show that LLMs fail at abductive reasoning and CoT methods performance are task complexity and data domain dependant.
We present GenSPP, a selective rationalization framework that eliminates interlocking via genetic-based search
We propose the task of implicit misogyny detection as an Argumentative Reasoning task, by assessing the quality of LLMs in generating the warrants which require reasoning skills in order to be extracted.
We propose a Semantic Componential Analysis (SCA) framework for a cross-cultural and cross-domain analysis of hate speech definitions.
We present a comparative analysis between offensive and non-offensive instances with regard to the degree to which the 4 Gricean Maxims (Quality, Quantity, Manner, and Relevance) are flouted or violated.
We propose MAMKit, an open, publicly available, PyTorch toolkit that consolidates datasets and models, providing a standardized platform for experimentation.
We chart the landscape of available speech datasets for this domain, to highlight possible pitfalls and opportunities for improvement and promote fairness and diversity.
We develop novel annotation guidelines for sentence-level subjectivity detection, which are not limited to language-specific cues.
We present PejorativITy, a novel corpus of 1,200 manually annotated Italian tweets for pejorative language at the word level and misogyny at the sentence level.
We propose to frame disruptive situation detection as a speech emotion recognition task. To validate our hypotheses, we carry out an extensive experimental study focusing on the development of a model characterized by speaker/gender independence, robustness to noise, and robustness against multiple voices.
We propose multimodal argument mining for argumentative fallacy classification in political debates.
We study how propositions are combined inhigher-level structures and how the relations between propositionscan be predicted by NLP models.
We introduce ArgSciChat, a dataset of 41 argumentative dialogues between scientists on 20 NLP papers.
We posit that in this domain useful explanations of classifier outcomes can be provided by resorting to legal rationales.
We present Demosthenes, a novel corpus for argument mining in legal documents, composed of 40 decisions of the Court of Justice of the European Union on matters of fiscal state aid.
We propose a study on multimodal argument mining in the domain of political debates
We develop an artificial intelligence system for the analysis of the scientific literature by leveraging on recent developments in the field of Argument Mining.
AMICA is an argument mining-based search engine, specifically designed for the analysis of scientific literature related to Covid-19.