Guillermo Moncecchi

Ignacio Sastre, Guillermo Moncecchi, Aiala Rosá

The application of Large Language Models to Question Answering has shown great promise, but important challenges such as hallucinations and erroneous reasoning arise when using these models, particularly in knowledge-intensive, domain-specific tasks. To address these issues, we introduce Derivation Prompting, a novel prompting technique for the generation step of the Retrieval-Augmented Generation framework. Inspired by logic derivations, this method involves deriving conclusions from initial hypotheses through the systematic application of predefined rules. It constructs a derivation tree that is interpretable and adds control over the generation process. We applied this method in a specific case study, significantly reducing unacceptable answers compared to traditional RAG and long-context window methods.

Gabriel Mordecki, Guillermo Moncecchi, Javier Couto

We revise the definition of clickbait, which lacks current consensus, and argue that the creation of a curiosity gap is the key concept that distinguishes clickbait from other related phenomena such as sensationalism and headlines that do not deliver what they promise or diverge from the article. Therefore, we propose a new definition: clickbait is a technique for generating headlines and teasers that deliberately omit part of the information with the goal of raising the readers' curiosity, capturing their attention and enticing them to click. We introduce a new approach to clickbait detection datasets creation, by refining the concept limits and annotations criteria, minimizing the subjectivity in the decision as much as possible. Following it, we created and release TA1C (for Te Ahorré Un Click, Spanish for Saved You A Click), the first open source dataset for clickbait detection in Spanish. It consists of 3,500 tweets coming from 18 well known media sources, manually annotated and reaching a 0.825 Fleiss' K inter annotator agreement. We implement strong baselines that achieve 0.84 in F1-score.

Diego Garat, Guillermo Moncecchi, Dina Wonsever

Frame Semantic Parsing (FSP) entails identifying predicates and labeling their arguments according to Frame Semantics. This paper investigates the use of In-Context Learning (ICL) with Large Language Models (LLMs) to perform FSP without model fine-tuning. We propose a method that automatically generates task-specific prompts for the Frame Identification (FI) and Frame Semantic Role Labeling (FSRL) subtasks, relying solely on the FrameNet database. These prompts, constructed from frame definitions and annotated examples, are used to guide six different LLMs. Experiments are conducted on a subset of frames related to violent events. The method achieves competitive results, with F1 scores of 94.3% for FI and 77.4% for FSRL. The findings suggest that ICL offers a practical and effective alternative to traditional fine-tuning for domain-specific FSP tasks.

Santiago Castro, Luis Chiruzzo, Aiala Rosá et al.

Computational Humor involves several tasks, such as humor recognition, humor generation, and humor scoring, for which it is useful to have human-curated data. In this work we present a corpus of 27,000 tweets written in Spanish and crowd-annotated by their humor value and funniness score, with about four annotations per tweet, tagged by 1,300 people over the Internet. It is equally divided between tweets coming from humorous and non-humorous accounts. The inter-annotator agreement Krippendorff's alpha value is 0.5710. The dataset is available for general use and can serve as a basis for humor detection and as a first step to tackle subjectivity.

Santiago Castro, Matías Cubero, Diego Garat et al.

While humor has been historically studied from a psychological, cognitive and linguistic standpoint, its study from a computational perspective is an area yet to be explored in Computational Linguistics. There exist some previous works, but a characterization of humor that allows its automatic recognition and generation is far from being specified. In this work we build a crowdsourced corpus of labeled tweets, annotated according to its humor value, letting the annotators subjectively decide which are humorous. A humor classifier for Spanish tweets is assembled based on supervised learning, reaching a precision of 84% and a recall of 69%.