22 citations · 77 across the 28 of their papers we have counts for
31 papers
Probing the Geometry of Color Representations in Multilingual Language Models
Pablo Loyola, Edison Marrese-Taylor, Andrés Hoyos-Idrobo
Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic? We decompose color representations into two…
NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
Yuheng Huang, Jianlang Chen, Jiayang Song +6
Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain…
An empirical study of the effect of video encoders on Temporal Video Grounding
Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Edison Marrese-Taylor +1
Temporal video grounding is a fundamental task in computer vision, aiming to localize a natural language query in a long, untrimmed video. It has a key role in the scientific commu…
On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs
Lucie Kunitomo-Jacquin, Edison Marrese-Taylor, Ken Fukuda
Quantifying uncertainty in large language models (LLMs) is important for safety-critical applications because it helps spot incorrect answers, known as hallucinations. One major tr…
Image-Text Relation Prediction for Multilingual Tweets
Matīss Rikters, Edison Marrese-Taylor
Various social networks have been allowing media uploads for over a decade now. Still, it has not always been clear what is their relation with the posted text or even if there is…
Annotations for Exploring Food Tweets From Multiple Aspects
Matīss Rikters, Edison Marrese-Taylor, Rinalds Vīksna
This research builds upon the Latvian Twitter Eater Corpus (LTEC), which is focused on the narrow domain of tweets related to food, drinks, eating and drinking. LTEC has been colle…
Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
Cristian Rodriguez-Opazo, Ehsan Abbasnejad, Damien Teney +3
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolut…
KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques
Rui Yang, Haoran Liu, Edison Marrese-Taylor +8
Large language models (LLMs) have demonstrated impressive generative capabilities with the potential to innovate in medicine. However, the application of LLMs in real clinical sett…
Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Ehsan Abbasnejad +4
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various neural architectures, spanning Transformer-based models li…
Perceptual Structure in the Absence of Grounding for LLMs: The Impact of Abstractedness and Subjectivity in Color Language
Pablo Loyola, Edison Marrese-Taylor, Andres Hoyos-Idobro
The need for grounding in language understanding is an active research topic. Previous work has suggested that color perception and color language appear as a suitable test bed to…
Integrating UMLS Knowledge into Large Language Models for Medical Question Answering
Rui Yang, Edison Marrese-Taylor, Yuhe Ke +3
Large language models (LLMs) have demonstrated powerful text generation capabilities, bringing unprecedented innovation to the healthcare field. While LLMs hold immense promise for…
Target-Aware Contextual Political Bias Detection in News
Iffat Maab, Edison Marrese-Taylor, Yutaka Matsuo
Media bias detection requires comprehensive integration of information derived from multiple news sources. Sentence-level political bias detection in news is no exception, and has…
Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding
Erica K. Shimomoto, Edison Marrese-Taylor, Hiroya Takamura +3
This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a natural language sentence query, the goal is to recognize and determine tempora…
LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando +2
We propose LocFormer, a Transformer-based model for video grounding which operates at a constant memory footprint regardless of the video length, i.e. number of frames. LocFormer i…
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers
Machel Reid, Edison Marrese-Taylor, Yutaka Matsuo
Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently sug…
DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando +2
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query. Given a query sentence, the goal is to determine the start and e…
VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling
Machel Reid, Edison Marrese-Taylor, Yutaka Matsuo
In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminat…
A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
Edison Marrese-Taylor, Cristian Rodriguez-Opazo, Jorge A. Balazs +2
Despite the recent advances in opinion mining for written reviews, few works have tackled the problem on other sources of reviews. In light of this issue, we propose a multi-modal…
Combining Pretrained High-Resource Embeddings and Subword Representations for Low-Resource Languages
Machel Reid, Edison Marrese-Taylor, Yutaka Matsuo
The contrast between the need for large amounts of data for current Natural Language Processing (NLP) techniques, and the lack thereof, is accentuated in the case of African langua…
Variational Inference for Learning Representations of Natural Language Edits
Edison Marrese-Taylor, Machel Reid, Yutaka Matsuo
Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of th…
An Edit-centric Approach for Wikipedia Article Quality Assessment
Edison Marrese-Taylor, Pablo Loyola, Yutaka Matsuo
We propose an edit-centric approach to assess Wikipedia article quality as a complementary alternative to current full document-based techniques. Our model consists of a main class…
Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Fatemeh Sadat Saleh +2
This paper studies the problem of temporal moment localization in a long untrimmed video using natural language as the query. Given an untrimmed video and a sentence as the query,…
Deep contextualized word representations for detecting sarcasm and irony
Suzana Ilić, Edison Marrese-Taylor, Jorge A. Balazs +1
Predicting context-dependent and non-literal utterances like sarcastic and ironic expressions still remains a challenging task in NLP, as it goes beyond linguistic patterns, encomp…
IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations
Jorge A. Balazs, Edison Marrese-Taylor, Yutaka Matsuo
In this paper we describe our system designed for the WASSA 2018 Implicit Emotion Shared Task (IEST), which obtained 2 place out of 26 teams with a test macro F1 scor…