Browsing by Author "Mendoza Rocha, Marcelo Gabriel"

Now showing 1 - 13 of 13
  • Thumbnail Image
    Item
    A New Content-Based Image Retrieval System for SARS-CoV-2 Computer-Aided Diagnosis
    (2022) Molina, Gabriel; Mendoza Rocha, Marcelo Gabriel; Loayza, Ignacio; Núñez, Camilo; Araya, Mauricio; Castañeda, Víctor; Solar, Mauricio
  • Thumbnail Image
    Item
    Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations
    (ASSOC COMPUTATIONAL LINGUISTICS-ACL, 2021) Araujo Vasquez, Vladimir Giovanny; Villa, Andres; Mendoza Rocha, Marcelo Gabriel; Moens, Marie-Francine; Soto, Alvaro
    Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level representations. In this work, we propose to use ideas from predictive coding theory to augment BERT-style language models with a mechanism that allows them to learn suitable discourse-level representations. As a result, our proposed approach is able to predict future sentences using explicit top-down connections that operate at the intermediate layers of the network. By experimenting with benchmarks designed to evaluate discourse-related knowledge using pre-trained sentence representations, we demonstrate that our approach improves performance in 6 out of 11 tasks by excelling in discourse relationship detection.
  • Thumbnail Image
    Item
    Bimodal Style Transference from Musical Composition to Image Using Deep Generative Models
    (2023) Apolo, María José; Mendoza Rocha, Marcelo Gabriel
  • Thumbnail Image
    Item
    CLNews: The First Dataset of the Chilean Social Outbreak for Disinformation Analysis
    (Association for Computing Machinery, 2022) Providel, Eliana; Toro, Daniel; Riquelme, Fabián; Mendoza Rocha, Marcelo Gabriel; Puraivan, E.
    Disinformation is one of the main threats that loom on social networks. Detecting disinformation is not trivial and requires training and maintaining fact-checking teams, which is labor-intensive. Recent studies show that the propagation structure of claims and user messages allows a better understanding of rumor dynamics. Despite these findings, the availability of verified claims and structural propagation data is low. This paper presents a new dataset with Twitter claims verified by fact-checkers along with the propagation structure of retweets and replies. The dataset contains verified claims checked during the Chilean social outbreak, which allows for studying the phenomenon of disinformation during this crisis. We study propagation patterns of verified content in CLNews, showing differences between false rumors and other types of content. Our results show that false rumors are more persistent than the rest of verified contents, reaching more people than truthful news and presenting low barriers of readability to users. The dataset is fully available and helps understand the phenomenon of disinformation during social crises being one of the first of its kind to be released.
  • No Thumbnail Available
    Item
    Cross-Lingual Cross-Domain Transfer Learning for Rumor Detection
    (2024) Providel, Eliana; Mendoza Rocha, Marcelo Gabriel; Solar, Mauricio
    This study introduces a novel method that merges propagation-based transfer learning with word embeddings for rumor detection. This approach aims to utilize data from languages with abundant resources to enhance performance in languages with limited availability of annotated corpora in this task. Furthermore, we augment our rumor detection framework with two supplementary tasks -stance classification and bot detection- to reinforce the primary task of rumor detection. Utilizing our proposed multi-task system, we generate several pretrained models that are subsequently fine-tuned for rumor detection in English. The results indicate significant improvements over baselines, thereby empirically validating the efficacy of our proposed approach. Although a direct metric comparison is difficult, given the different datasets and techniques used in the state-of-the-art, we compare our proposal with 20 other works that target rumor detection in English. By combining stance classification and bot detection as auxiliary tasks, we achieve a Macro-F1 of 0.914. On the other hand, we achieve a Macro-F1 of 0.804 for the Spanish language. In both cases, we beat baseline results, evidencing the proposed approach's usefulness
  • No Thumbnail Available
    Item
    Ethics in Artificial Intelligence and Information Technologies
    (CRC Press, 2025) Arriagada Bruneau, Gabriela Constanza; Lopez Moncada, Claudia; Mendoza Rocha, Marcelo Gabriel
    This book addresses the challenges posed by adopting and developing new AI technologies and how they impact people. Ethics, the scope, and the impact of technology on people are vital. The book starts with the ethical aspects of AI, presenting a socio-technical approach to integrating Ethics into AI projects, and outlines perspectives around feminism, sustainability, and labor transformation. Next, the concepts of fairness, accountability, and transparency are introduced, discussing their implications for developing information systems such as recommender systems, including aspects related to data privacy. Then the book covers the relevance of natural language processing systems, highlighting debias strategies and evaluation methodologies. The scopes of fairness-based approaches for ChatGPT and other generative text models are also introduced. Finally, advanced topics that include the relationship between AI and disinformation are addressed, including a discussion of the scope of news-generative models such as deep fakes. The book ends with a discussion of the perspectives and challenges in the area. The book is meant for an audience of advanced undergraduate and graduate students from all disciplines related to information systems. It is also helpful for researchers and practitioners interested in the subject.
  • Thumbnail Image
    Item
    Exploring the Impact of Generative AI for StandUp Report Recommendations in Software Capstone Project Development
    (2024) Neyem, Hugo Andrés; Sandoval Alcocer, Juan Pablo; Mendoza Rocha, Marcelo Gabriel; Centellas-Claro, Leonardo; González, Luis A.; Paredes Robles, Carlos Daniel
    StandUp Reports play an important role in capstone software engineering courses, facilitating progress tracking, obstacle identification, and team collaboration. However, despite their significance, students often grapple with the challenge of creating StandUp Reports that are clear, concise, and actionable. This paper investigates the impact of the use of generative AI in producing StandUp report recommendations, aiming to assist students in enhancing the quality and effectiveness of their reports. In a semester-long capstone course, 179 students participated in 16 real-world software development projects. They submitted weekly StandUp Reports with the assistance of an AI-powered Slack, which analyzed their initial reports and provided suggestions for enhancing them using both GPT-3.5 and the early access GPT-4 API. After each submitted report, students voluntarily answered a survey about usability and suggestion preference. Furthermore, we conducted a linguistic analysis of the recommendations made by the algorithms to gauge reading ease and comprehension complexity. Our findings indicate that the AI-based recommendation system helped students improve the overall quality of their StandUp Reports throughout the semester. Students expressed a high level of satisfaction with the tool and exhibited a strong willingness to continue using it in the future. The survey reveals that students perceived a slight improvement when using GPT-4 compared to GPT-3.5. Finally, a computational linguistic analysis performed on the recommendations demonstrates that both algorithms significantly improve the alignment between the generated texts and the students' educational level, thereby improving the quality of the original texts.
  • Thumbnail Image
    Item
    Inspecting the concept knowledge graph encoded by modern language models
    (Association for Computational Linguistics (ACL), 2021) Aspillaga, Carlos; Soto, Alvaro; Mendoza Rocha, Marcelo Gabriel
    The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researchers to study the underlying knowledge encoded by these models. Despite this, attempts to understand their semantic capabilities have not been successful, often leading to non-conclusive, or contradictory conclusions among different works. Via a probing classifier, we extract the underlying knowledge graph of nine of the most influential language models of the last years, including word embeddings, text generators, and context encoders. This probe is based on concept relatedness, grounded on WordNet. Our results reveal that all the models encode this knowledge, but suffer from several inaccuracies. Furthermore, we show that the different architectures and training strategies lead to different model biases. We conduct a systematic evaluation to discover specific factors that explain why some concepts are challenging. We hope our insights will motivate the development of models that capture concepts more precisely.
  • No Thumbnail Available
    Item
    Reducing interpretative ambiguity in an educational environment with ChatGPT
    (Elsevier Ltd, 2025) García Varela, Francisco José Andrés; Bekerman, Z.; Nussbaum Voehl, Miguel; Mendoza Rocha, Marcelo Gabriel; Montero, Joaquín
    The study posits that both concrete and abstract words are crucial for effective communication, particularly in educational contexts where the interplay between these forms of language intersects with linguistic, cognitive, and social stratification theories. A key challenge is balancing the efficiency of abstract language in conveying complex concepts with the accessibility of concrete language, which enhances student comprehension. Generative languages, with their capacity to manipulate symbols, offer a way to navigate this challenge by facilitating the structured and systematic representation and exploration of abstract concepts within their contexts. The central research question was: “How can generative languages assist educational stakeholders in articulating their ideas and actions more clearly by identifying and refining abstract terms?” To explore this, a protocol in English was developed for ChatGPT-4, featuring structured guidelines and prompts aimed at helping users achieve specific educational goals. In a pilot study involving 13 participants, ChatGPT-4 provided feedback, suggested improvements, and guided users through text interactions. One of the authors observed the participants, took notes on their behavior, and conducted brief post-exercise discussions to gauge their experiences. After the session, participants were asked to reflect on their experience and share their thoughts via email. The process helped participants refine their responses from abstract to more concrete terms, enhancing clarity and engagement with educational content. The ChatGPT-4 protocol effectively bridges the gap between abstract pedagogical theories and practical classroom application, training teachers to use vivid descriptions, relatable scenarios, and tangible examples. This study illustrates how artificial intelligence can successfully integrate teaching principles and learning theories to enhance educational practices.
  • Thumbnail Image
    Item
    SpatialCluster: A Python library for urban clustering
    (Elsevier B.V., 2024) Reyes A.; Mendoza Rocha, Marcelo Gabriel; Vera, Camila; Lucchini Wortzman, Francesca; Dimter J.; Gutierrez F.; Bro N.; Lobel Díaz, Hans Albert; Reyes A.
    This paper introduces SpatialCluster, a Python library developed for clustering urban areas using geolocated data. The library integrates a range of methods for urban clustering, including Deep Modularity Networks, Gaussian Mixtures, K-Nearest Neighbours, Self Organized Maps, and Information-Theoretic Clustering, providing a comprehensive framework. These methods are evaluated using indices such as the Adjusted Rand Index and Adjusted Mutual Information, and the library includes features for detailed map visualization. SpatialCluster's online documentation offers examples, making the library accessible to researchers and urban planners. The library aims to facilitate urban data analysis and contribute to the field of urban studies.
  • Thumbnail Image
    Item
    Supporting Users in Refining and Comparing Topic Models: An Experimental Study
    (2023) González-Pizarro, F.; Moncada, C.L.; Milios, E.V.; Paulovich, F.; Mendoza Rocha, Marcelo Gabriel
  • Thumbnail Image
    Item
    Towards an AI Knowledge Assistant for Context-aware Learning Experiences in Software Capstone Project Development
    (2024) Neyem, Hugo Andres; González, Luis A.; Mendoza Rocha, Marcelo Gabriel; Sandoval Alcocer, Juan Pablo; Centellas, Leonardo; Paredes, Carlos
    Software assistants have significantly impacted software development for both practitioners and students, particularly in capstone projects. The effectiveness of these tools varies based on their knowledge sources; assistants with localized, domain-specific knowledge may have limitations, while tools like ChatGPT, using broad datasets, might offer recommendations that do not always match the specific objectives of a capstone course. Addressing a gap in current educational technology, this paper introduces an AI Knowledge Assistant specifically designed to overcome the limitations of existing tools by enhancing the quality and relevance of Large Language Models (LLMs). It achieves this through the innovative integration of contextual knowledge from a local “lessons learned” database tailored to the capstone course. We conducted a study with 150 students using the assistant during their capstone course. Integrated into the Kanban project tracking system, the assistant offered recommendations using different strategies: direct searches in the lessons learned database, direct queries to a GPT model, query enrichment with lessons learned before submission to GPT and LLaMa models, and query enhancement with Stack Overflow data before GPT processing. Survey results underscored a strong preference among students for direct LLM queries and those enriched with local repository insights, highlighting the assistant's practical value. Further, our linguistic analysis conclusively demonstrated that texts generated by the LLM closely mirrored the linguistic standards and topical relevance of university course requirements. This alignment not only fosters a deeper understanding of course content but also significantly enhances the material's applicability to real-world scenarios.
  • Thumbnail Image
    Item
    VICTOR VECTORS @ DIPROMATS 2024: Propaganda Detection with LLM Paraphrasing and Machine Translation
    (CEUR-WS, 2024) Fernández, Miguel; Ojeda Aguila, Maximiliano Eduardo; Guevara, Lilly; Varela, Diego; Mendoza Rocha, Marcelo Gabriel; Barrón-Cedeno, Alberto
    Identifying propaganda in social media posts is an important task that can help to better understand the strategies applied by policy makers and stake holders when trying to convey their message to the general public. We describe our participation in DIPROMATS 2024 Task 1 on the automated detection and characterization of propaganda techniques and narratives from diplomats of major powers. We show an efficient way to utilize Large Language Models (LLMs) to paraphrase a sample of the training instances, to balance the class distribution in the datasets provided by the shared task. Our submission ranked 1st in Subtask-1a in English (ICM score of 0.2123) and 1st in the bilingual evaluation (ICM score of 0.2048). We also achieved top-3 rankings in Spanish and subtasks 1b and 1c.