Výsledky vyhledávání - "Teruel, Milagro"

Report

Transforming Human-Centered AI Collaboration: Redefining Embodied Agents Capabilities through Interactive Grounded Language Instructions

Autor: Mohanty, Shrestha, Arabzadeh, Negar, Kiseleva, Julia, Zholus, Artem, Teruel, Milagro, Awadallah, Ahmed, Sun, Yuxuan, Srinet, Kavya, Szlam, Arthur

Human intelligence's adaptability is remarkable, allowing us to adjust to new tasks and multi-modal environments swiftly. This skill is evident from a young age as we acquire new abilities and solve problems by imitating others or following natural l

Externí odkaz: http://arxiv.org/abs/2305.10783

Zobrazit plný text záznamu

Report

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback

Autor: Mehta, Nikhil, Teruel, Milagro, Sanz, Patricio Figueroa, Deng, Xin, Awadallah, Ahmed Hassan, Kiseleva, Julia

Many approaches to Natural Language Processing (NLP) tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, human language is inherently interactive,

Externí odkaz: http://arxiv.org/abs/2304.10750

Zobrazit plný text záznamu

Report

On Improving Summarization Factual Consistency from Natural Language Feedback

Autor: Liu, Yixin, Deb, Budhaditya, Teruel, Milagro, Halfaker, Aaron, Radev, Dragomir, Awadallah, Ahmed H.

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and user preferen

Externí odkaz: http://arxiv.org/abs/2212.09968

Zobrazit plný text záznamu

Report

Collecting Interactive Multi-modal Datasets for Grounded Language Understanding

Autor: Mohanty, Shrestha, Arabzadeh, Negar, Teruel, Milagro, Sun, Yuxuan, Zholus, Artem, Skrynnik, Alexey, Burtsev, Mikhail, Srinet, Kavya, Panov, Aleksandr, Szlam, Arthur, Côté, Marc-Alexandre, Kiseleva, Julia

Publikováno v: Interactive Learning for Natural Language Processing NeurIPS 2022 Workshop

Human intelligence can remarkably adapt quickly to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural lang

Externí odkaz: http://arxiv.org/abs/2211.06552

Zobrazit plný text záznamu

Report

Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions

Autor: Skrynnik, Alexey, Volovikova, Zoya, Côté, Marc-Alexandre, Voronov, Anton, Zholus, Artem, Arabzadeh, Negar, Mohanty, Shrestha, Teruel, Milagro, Awadallah, Ahmed, Panov, Aleksandr, Burtsev, Mikhail, Kiseleva, Julia

The adoption of pre-trained language models to generate action plans for embodied agents is a promising research strategy. However, execution of instructions in real or simulated environments requires verification of the feasibility of actions as wel

Externí odkaz: http://arxiv.org/abs/2211.00688

Zobrazit plný text záznamu

Report

IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022

Autor: Kiseleva, Julia, Skrynnik, Alexey, Zholus, Artem, Mohanty, Shrestha, Arabzadeh, Negar, Côté, Marc-Alexandre, Aliannejadi, Mohammad, Teruel, Milagro, Li, Ziming, Burtsev, Mikhail, ter Hoeve, Maartje, Volovikova, Zoya, Panov, Aleksandr, Sun, Yuxuan, Srinet, Kavya, Szlam, Arthur, Awadallah, Ahmed

Human intelligence has the remarkable ability to adapt to new tasks and environments quickly. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provid

Externí odkaz: http://arxiv.org/abs/2205.13771

Zobrazit plný text záznamu

Estudio de representaciones mediante co-embeddings para estudiantes y contenidos en minerı́a de datos educativos

Autor: Teruel, Milagro

Publikováno v: Repositorio Digital Universitario (UNC)
Universidad Nacional de Córdoba
instacron:UNC

Tesis (Doctora en Ciencias de la Computación)--Universidad Nacional de Córdoba, Facultad de Matemática, Astronomía, Física y Computación, 2019. Este trabajo es un estudio sobre la generación automática de representaciones basadas en métodos

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::bd55cba3c746442bc0ce56b75770fc29

Zobrazit plný text záznamu

Different Flavors of Attention Networks for Argument Mining

Autor: Frau, Johanna, Teruel, Milagro, Alonso Alemany, Laura, Villata, Serena

Publikováno v: FLAIRS 2019-32th International Florida Artificial Intelligence Research Society Conference
FLAIRS 2019-32th International Florida Artificial Intelligence Research Society Conference, May 2019, Sarasota, United States

International audience; Argument mining is a rising area of Natural Language Processing (NLP) concerned with the automatic recognition and interpretation of argument components and their relations. Neural models are by now mature technologies to be e

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::07f64eea0769e51f452504f3e18d46cf
https://hal.science/hal-02381078/file/18298-78917-1-PB.pdf

Zobrazit plný text záznamu

Convolutional Ladder Networks for Legal {NERC} and the Impact of Unsupervised Data in Better Generalizations

Autor: Cardellino, Cristian, Alonso Alemany, Laura, Teruel, Milagro, Villata, Serena, Marro, Santiago

International audience; In this paper we adapt the semi-supervised deep learning architecture known as "Convolutional Ladder Networks", from the domain of computer vision, and explore how well it works for a semi-supervised Named Entity Recognition a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ac06faddb08f0ae2630fe2c74e5887bf
https://hal.archives-ouvertes.fr/hal-02381093/file/18295-78914-1-PB.pdf

Zobrazit plný text záznamu

Increasing Argument Annotation Reproducibility by Using Inter-annotator Agreement to Improve Guidelines

Autor: Teruel, Milagro, Cardellino, Cristian, Cardellino, Fernando, Alonso Alemany, Laura, Villata, Serena

Publikováno v: Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018
LREC 2018-11th International Conference on Language Resources and Evaluation
LREC 2018-11th International Conference on Language Resources and Evaluation, May 2018, Miyazaki, Japan. pp.1-4

International audience; In this abstract we present a methodology to improve Argument annotation guidelines by exploiting inter-annotator agreement measures.After a first stage of the annotation effort, we have detected problematic issues via an anal

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::98fca41b3910303edde5434b9409490f
https://hal.science/hal-01876506

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání