Zobrazeno 1 - 10
of 7 436
pro vyhledávání: '"A A Alabi"'
In this work, we present Yor\`ub\'a automatic diacritization (YAD) benchmark dataset for evaluating Yor\`ub\'a diacritization systems. In addition, we pre-train text-to-text transformer, T5 model for Yor\`ub\'a and showed that this model outperform s
Externí odkaz:
http://arxiv.org/abs/2412.20218
Autor:
Bayes, Edward, Azime, Israel Abebe, Alabi, Jesujoba O., Kgomo, Jonas, Eloundou, Tyna, Proehl, Elizabeth, Chen, Kai, Khadir, Imaan, Etori, Naome A., Muhammad, Shamsuddeen Hassan, Mpanza, Choice, Thete, Igneciah Pocia, Klakow, Dietrich, Adelani, David Ifeoluwa
Evaluations of Large Language Models (LLMs) on knowledge-intensive tasks and factual accuracy often focus on high-resource languages primarily because datasets for low-resource languages (LRLs) are scarce. In this paper, we present Uhura -- a new ben
Externí odkaz:
http://arxiv.org/abs/2412.00948
Robots are now increasingly integrated into various real world applications and domains. In these new domains, robots are mostly employed to improve, in some ways, the work done by humans. So, the need for effective Human-Robot Teaming (HRT) capabili
Externí odkaz:
http://arxiv.org/abs/2408.12823
Autor:
Rohanian, Omid, Nouriborji, Mohammadmahdi, Seminog, Olena, Furst, Rodrigo, Mendy, Thomas, Levanita, Shanthi, Kadri-Alabi, Zaharat, Jabin, Nusrat, Toale, Daniela, Humphreys, Georgina, Antonio, Emilia, Bucher, Adrian, Norton, Alice, Clifton, David A.
This paper introduces the Pandemic PACT Advanced Categorisation Engine (PPACE) along with its associated dataset. PPACE is a fine-tuned model developed to automatically classify research abstracts from funded biomedical projects according to WHO-alig
Externí odkaz:
http://arxiv.org/abs/2407.10086
Autor:
Adelani, David Ifeoluwa, Ojo, Jessica, Azime, Israel Abebe, Zhuang, Jian Yun, Alabi, Jesujoba O., He, Xuanli, Ochieng, Millicent, Hooker, Sara, Bukula, Andiswa, Lee, En-Shiun Annie, Chukwuneke, Chiamaka, Buzaaba, Happy, Sibanda, Blessing, Kalipe, Godson, Mukiibi, Jonathan, Kabongo, Salomon, Yuehgoh, Foutse, Setaka, Mmasibidi, Ndolela, Lolwethu, Odu, Nkiruka, Mabuya, Rooweither, Muhammad, Shamsuddeen Hassan, Osei, Salomey, Samb, Sokhar, Guge, Tadesse Kebede, Stenetorp, Pontus
Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource languages (e.g. African languages) are often evaluated only on basic text
Externí odkaz:
http://arxiv.org/abs/2406.03368
Autor:
Ilevbare, Comfort Eseohen, Alabi, Jesujoba O., Adelani, David Ifeoluwa, Bakare, Firdous Damilola, Abiola, Oluwatoyin Bunmi, Adeyemo, Oluwaseyi Adesina
Nigerians have a notable online presence and actively discuss political and topical matters. This was particularly evident throughout the 2023 general election, where Twitter was used for campaigning, fact-checking and verification, and even positive
Externí odkaz:
http://arxiv.org/abs/2404.18180
This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages. The shared task aims at measuring the semantic textual relatedness between pairs of sentences, with a focus on a range
Externí odkaz:
http://arxiv.org/abs/2404.01490
Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. Current RRG approaches are still unsatisfactory against clinical standards. This paper introduces a novel RRG method, \
Externí odkaz:
http://arxiv.org/abs/2403.06728
Autor:
Zhang, Miaoran, Gautam, Vagrant, Wang, Mingyang, Alabi, Jesujoba O., Shen, Xiaoyu, Klakow, Dietrich, Mosbach, Marius
In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without needing any parameter updates. Although there have been extensive studies on English in-context learning, mul
Externí odkaz:
http://arxiv.org/abs/2402.12976
Publikováno v:
Engineering, Construction and Architectural Management, 2023, Vol. 32, Issue 1, pp. 673-704.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/ECAM-01-2023-0024
